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

S
SegmentFault 最新的问题
J
Java Code Geeks
V
V2EX
Blog — PlanetScale
Blog — PlanetScale
博客园 - 司徒正美
Hugging Face - Blog
Hugging Face - Blog
F
Fortinet All Blogs
aimingoo的专栏
aimingoo的专栏
B
Blog
A
About on SuperTechFans
有赞技术团队
有赞技术团队
月光博客
月光博客
Microsoft Azure Blog
Microsoft Azure Blog
阮一峰的网络日志
阮一峰的网络日志
腾讯CDC
美团技术团队
大猫的无限游戏
大猫的无限游戏
爱范儿
爱范儿
N
Netflix TechBlog - Medium
C
Check Point Blog
Recent Announcements
Recent Announcements
博客园 - Franky
博客园 - 叶小钗
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
chore(config): refresh post-compaction guard labels · ope...
steipete · 2026-05-05 · via Recent Commits to openclaw:main

@@ -18274,13 +18274,15 @@ export const GENERATED_BASE_CONFIG_SCHEMA: BaseConfigSchemaResponse = {

1827418274

properties: {

1827518275

enabled: {

1827618276

type: "boolean",

18277+

title: "Post-compaction Loop Guard",

1827718278

description:

1827818279

"Enable the post-compaction loop guard that aborts the run when the agent repeats the same (tool, args, result) triple windowSize times immediately after auto-compaction-retry (default: true).",

1827918280

},

1828018281

windowSize: {

1828118282

type: "integer",

1828218283

exclusiveMinimum: 0,

1828318284

maximum: 9007199254740991,

18285+

title: "Post-compaction Loop Guard Window Size",

1828418286

description:

1828518287

"Number of post-compaction attempts during which the guard stays armed (default: 3). Lower values are stricter; higher values give the agent more attempts before abort.",

1828618288

},

@@ -25647,6 +25649,16 @@ export const GENERATED_BASE_CONFIG_SCHEMA: BaseConfigSchemaResponse = {

2564725649

help: "Global no-progress breaker threshold (default: 30).",

2564825650

tags: ["reliability", "tools"],

2564925651

},

25652+

"tools.loopDetection.postCompactionGuard.enabled": {

25653+

label: "Post-compaction Loop Guard",

25654+

help: "Enable the post-compaction loop guard that aborts the run when the agent repeats the same (tool, args, result) triple windowSize times immediately after auto-compaction-retry (default: true).",

25655+

tags: ["tools"],

25656+

},

25657+

"tools.loopDetection.postCompactionGuard.windowSize": {

25658+

label: "Post-compaction Loop Guard Window Size",

25659+

help: "Number of post-compaction attempts during which the guard stays armed (default: 3). Lower values are stricter; higher values give the agent more attempts before abort.",

25660+

tags: ["tools"],

25661+

},

2565025662

"tools.loopDetection.detectors.genericRepeat": {

2565125663

label: "Tool-loop Generic Repeat Detection",

2565225664

help: "Enable generic repeated same-tool/same-params loop detection (default: true).",

@@ -29004,14 +29016,6 @@ export const GENERATED_BASE_CONFIG_SCHEMA: BaseConfigSchemaResponse = {

2900429016

help: "Plugin-defined configuration payload interpreted by that plugin's own schema and validation rules. Use only documented fields from the plugin to prevent ignored or invalid settings.",

2900529017

tags: ["advanced"],

2900629018

},

29007-

"tools.loopDetection.postCompactionGuard.enabled": {

29008-

help: "Enable the post-compaction loop guard that aborts the run when the agent repeats the same (tool, args, result) triple windowSize times immediately after auto-compaction-retry (default: true).",

29009-

tags: ["tools"],

29010-

},

29011-

"tools.loopDetection.postCompactionGuard.windowSize": {

29012-

help: "Number of post-compaction attempts during which the guard stays armed (default: 3). Lower values are stricter; higher values give the agent more attempts before abort.",

29013-

tags: ["tools"],

29014-

},

2901529019

"models.providers.*.headers.*": {

2901629020

sensitive: true,

2901729021

tags: ["security", "models"],