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

Blog — PlanetScale
Blog — PlanetScale
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
Vercel News
Vercel News
B
Blog
腾讯CDC
P
Proofpoint News Feed
Google DeepMind News
Google DeepMind News
N
Netflix TechBlog - Medium
L
LangChain Blog
F
Fortinet All Blogs
T
The Blog of Author Tim Ferriss
人人都是产品经理
人人都是产品经理
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
I
InfoQ
IT之家
IT之家
酷 壳 – CoolShell
酷 壳 – CoolShell
aimingoo的专栏
aimingoo的专栏
D
DataBreaches.Net
Stack Overflow Blog
Stack Overflow Blog
The Cloudflare Blog
Last Week in AI
Last Week in AI
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
博客园 - 三生石上(FineUI控件)
T
Tailwind CSS 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
refactor(agents): simplify cli session recovery probes · ...
obviyus · 2026-05-30 · via Recent Commits to openclaw:main

@@ -784,8 +784,6 @@ describe("claudeCliSessionTranscriptHasOrphanedToolUse", () => {

784784

});

785785786786

it("returns true when the last assistant message has a trailing tool_use without tool_result", async () => {

787-

// Reproduces the 3d-engineer stuck-resume scenario: gateway died after

788-

// claude emitted tool_use(Bash) but before the tool_result was flushed.

789787

await writeJsonlSession("orphan", [

790788

{

791789

type: "assistant",

@@ -838,9 +836,6 @@ describe("claudeCliSessionTranscriptHasOrphanedToolUse", () => {

838836

});

839837840838

it("returns false when an earlier assistant tool_use is unanswered but the last assistant message resolved cleanly", async () => {

841-

// Edge case: an unanswered tool_use deep in history is INERT — it

842-

// can't block forward progress because a later assistant message

843-

// already moved past it. Only TRAILING orphans matter.

844839

await writeJsonlSession("buried", [

845840

{

846841

type: "assistant",

@@ -875,19 +870,11 @@ describe("claudeCliSessionTranscriptHasOrphanedToolUse", () => {

875870

});

876871877872

it("ignores sidechain entries when deciding orphans (matches main-history importer's skip rule)", async () => {

878-

// A trailing sidechain (Task-tool / subagent) `tool_use` without a

879-

// matching `tool_result` is NOT a forward-progress blocker for the

880-

// main conversation. The existing history importer at

881-

// gateway/cli-session-history.claude.ts skips `isSidechain === true`

882-

// entries; this probe must do the same or it will falsely invalidate

883-

// healthy main-conversation resumes that happen to have a sidechain

884-

// unanswered tool_use near the tail.

885873

await writeJsonlSession("sidechain-trailing", [

886874

{

887875

type: "assistant",

888876

message: { role: "assistant", content: [{ type: "text", text: "ok" }] },

889877

},

890-

// Sidechain assistant with unanswered tool_use — should be ignored.

891878

{

892879

isSidechain: true,

893880

type: "assistant",

@@ -908,15 +895,13 @@ describe("claudeCliSessionTranscriptHasOrphanedToolUse", () => {

908895909896

it("still flags a main-conversation orphan even when sidechain entries exist alongside", async () => {

910897

await writeJsonlSession("main-orphan-with-sidechain", [

911-

// Main assistant orphan

912898

{

913899

type: "assistant",

914900

message: {

915901

role: "assistant",

916902

content: [{ type: "tool_use", id: "toolu_main_orphan", name: "Bash", input: {} }],

917903

},

918904

},

919-

// Sidechain entries after that don't help the orphan get answered.

920905

{

921906

isSidechain: true,

922907

type: "user",

@@ -938,9 +923,6 @@ describe("claudeCliSessionTranscriptHasOrphanedToolUse", () => {

938923

});

939924940925

it("inspects the transcript tail past 500 records (does not inherit the content-probe cap)", async () => {

941-

// 600 user-pings + 1 healthy-and-resolved tool turn + 1 trailing

942-

// orphan tool_use. A capped walk that stops at record 500 would

943-

// never see the orphan and incorrectly return false (resume hangs).

944926

const lines: object[] = [];

945927

for (let i = 0; i < 600; i++) {

946928

lines.push({

@@ -980,9 +962,6 @@ describe("claudeCliSessionTranscriptHasOrphanedToolUse", () => {

980962

});

981963982964

it("does not falsely flag a long transcript whose orphan was resolved past record 500", async () => {

983-

// 600 user-pings + early tool_use + 100 user-pings + late tool_result

984-

// resolving it. A capped walk would stop before reaching the

985-

// tool_result and return true (false positive → unnecessary reset).

986965

const lines: object[] = [];

987966

lines.push({

988967

type: "assistant",