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

量子位
Google DeepMind News
Google DeepMind News
爱范儿
爱范儿
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
NISL@THU
NISL@THU
T
Threat Research - Cisco Blogs
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
L
Lohrmann on Cybersecurity
V
Visual Studio Blog
Cyberwarzone
Cyberwarzone
D
Docker
The Hacker News
The Hacker News
C
CERT Recently Published Vulnerability Notes
Vercel News
Vercel News
Project Zero
Project Zero
S
Schneier on Security
aimingoo的专栏
aimingoo的专栏
I
Intezer
腾讯CDC
M
MIT News - Artificial intelligence
Hugging Face - Blog
Hugging Face - Blog
P
Palo Alto Networks Blog
C
CXSECURITY Database RSS Feed - CXSecurity.com
AWS News Blog
AWS News Blog
GbyAI
GbyAI
MongoDB | Blog
MongoDB | Blog
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
V
Vulnerabilities – Threatpost
G
Google Developers Blog
N
Netflix TechBlog - Medium
The Cloudflare Blog
Microsoft Security Blog
Microsoft Security Blog
Y
Y Combinator Blog
A
Arctic Wolf
S
Securelist
酷 壳 – CoolShell
酷 壳 – CoolShell
Cisco Talos Blog
Cisco Talos Blog
Recent Announcements
Recent Announcements
C
Cyber Attacks, Cyber Crime and Cyber Security
L
LINUX DO - 热门话题
T
Threatpost
Latest news
Latest news
Blog — PlanetScale
Blog — PlanetScale
Security Latest
Security Latest
Engineering at Meta
Engineering at Meta
大猫的无限游戏
大猫的无限游戏
H
Help Net Security
The GitHub Blog
The GitHub Blog
T
Tor Project blog
P
Proofpoint News Feed

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: trim doctor command hotspots · openclaw/openclaw@c66f16a test: isolate agent auth and spawn hotspots · openclaw/openclaw@9285935 test: stabilize MCP startup disposal race · openclaw/openclaw@dd9d2eb test: merge browser contract server suites · openclaw/openclaw@5817a76 test: narrow ollama provider discovery setup · openclaw/openclaw@a0d9598 build: declare qa-lab aimock runtime dependency · openclaw/openclaw@24431e5 test: speed up safe-bins exec harness · openclaw/openclaw@ee856ab test: preserve tool helpers in embedded runner mocks · openclaw/openclaw@acd86a0 refactor: move memory embeddings into provider plugins · openclaw/openclaw@77e6e4c test: reuse system-run temp fixtures · openclaw/openclaw@7e9ff0f test: trim hotspot wait overhead · openclaw/openclaw@12a59b0 Check: avoid duplicate boundary prep · openclaw/openclaw@baf11b8 test: reduce hotspot fixture overhead · openclaw/openclaw@3a59edd feat(ui): overhaul settings and slash command UX (#67819) thanks @Bun… · openclaw/openclaw@2cfb660 QA Matrix: exit cleanly on failure · openclaw/openclaw@42805d2 QA Matrix: isolate scenario coverage · openclaw/openclaw@7e659e1 Matrix: refresh crypto bootstrap state · openclaw/openclaw@94081d8 QA Lab: add provider registry · openclaw/openclaw@bb7e982 Matrix: add plugin changelog · openclaw/openclaw@4acab55 test: trim more hotspot overhead · openclaw/openclaw@f485311 test: trim remaining hotspot tests · openclaw/openclaw@6ba8626 test: narrow hotspot mocks · openclaw/openclaw@dbc8179 test: isolate gemini embedding request helpers · openclaw/openclaw@cd330f5 test: trim memory and mcp hotspots · openclaw/openclaw@fd48dfa test: slim provider registry mocks · openclaw/openclaw@2e08c77 test: harden Parallels update smoke · openclaw/openclaw@1a98090 feat: default Anthropic to Opus 4.7 · openclaw/openclaw@628b454 fix: harden node-host shell payload mutability checks · openclaw/openclaw@75c551e fix: land node-host approval binding for native binaries (#66731) (th… · openclaw/openclaw@29919bb CI: add daily schedule to CodeQL workflow (#67645) · openclaw/openclaw@69d25f5 fix(gateway): capture config hash after plugin auto-enable to prevent… · openclaw/openclaw@8c11210 fix: repair sanitized replay tool results before send (#67620) (thank… · openclaw/openclaw@c3c7a99 fix: restrict HTML timeout short-circuit to transient statuses · openclaw/openclaw@de129a6 fix: keep TUI watchdog bound to active run (#67401) (thanks @xantorres) · openclaw/openclaw@3525273 Gateway/skills: dedupe skills prefix-match + drop dead fallback on log · openclaw/openclaw@d7f489f Extensions/lmstudio: back off inference preload after consecutive fai… · openclaw/openclaw@b555214 TUI/streaming: add watchdog that resets the activity indicator after … · openclaw/openclaw@f44ab20 Agents/tool-loop: enable unknown-tool stream guard by default · openclaw/openclaw@36ed367 Gateway/skills: invalidate session skills snapshot on config write · openclaw/openclaw@b23d59a fix: classify HTML provider error pages correctly (#67642) (thanks @s… · openclaw/openclaw@e588e90 fix(skills): remove unused model-usage import (#67641) · openclaw/openclaw@55f05df docs(changelog): credit codex fix superseded PRs · openclaw/openclaw@e485f24 fix(openai-codex): normalize stale transport metadata in resolution a… · openclaw/openclaw@90801ba CI: pin Docker-related GitHub Actions (#67632) · openclaw/openclaw@f697b01 Android: modernize WebView and discovery API usage (#67627) · openclaw/openclaw@44a6e50 fix(deps): bump hono to 4.12.14 and @hono/node-server to 1.19.14 (GHS… · openclaw/openclaw@fbccc18 fix(deps): bump dompurify to 3.4.0 (#67614) · openclaw/openclaw@2c2dc00 CI: add explicit permissions to all workflow jobs (fixes code-scannin… · openclaw/openclaw@01b7516 fix: register bundled TTS providers and route overrides correctly (#6… · openclaw/openclaw@6ea3cdd fix: align host tilde paths with OS home (#62804) (thanks @stainlu) · openclaw/openclaw@ecfaf64 fix: flush creds queue before reconnect socket open (#67464) (thanks … · openclaw/openclaw@405c63f fix: strip standalone <function> tool call tags from visible text (#6… · openclaw/openclaw@78df859 fix(agents): preserve cli session metadata before transcript persist … · openclaw/openclaw@898fd04 docs(changelog): move cli transcript entry · openclaw/openclaw@c1817c6 fix(agents): normalize cli transcript api field · openclaw/openclaw@3a3fae0 docs(changelog): note cli transcript persistence · openclaw/openclaw@6c343f1 fix(agents): persist cli transcript turns · openclaw/openclaw@b8ef507 fix(msteams): harden security-sensitive flows (#65841) · openclaw/openclaw@c56b56e [Dashboard] Fix exec approval modal overflow for long command content… · openclaw/openclaw@053c5b0 Docs: remove QA changelog entry · openclaw/openclaw@7fd5771 QA: fix private runtime source loading (#67428) · openclaw/openclaw@d5933af docs(gateway): correct protocol.md schema path, hello-ok example, aut… · openclaw/openclaw@489404d CI: pin Node 22 runners to 22.18.0 · openclaw/openclaw@4ffa621 models.authStatus: normalize provider ids + tighten env-backed escape… · openclaw/openclaw@f2fdb9d Update CHANGELOG.md · openclaw/openclaw@7694a92 test(parallels): clean up npm update guard jobs · openclaw/openclaw@045ea7b Plugins: prefer scanDir override paths · openclaw/openclaw@b2974da fix(dreaming): default storage.mode to "separate" so phase blocks sto… · openclaw/openclaw@8c392f0 fix(memory-core): skip dreaming transcript ingestion via session stor… · openclaw/openclaw@a1b01f0 fix: dedupe replayed exec.finished node events (#67281) · openclaw/openclaw@5dcf526
fix(anthropic): pass system prompt on resumed claude-cli sessions · openclaw/openclaw@84e6282
JanusAsmusse · 2026-05-27 · via Recent Commits to openclaw:main

@@ -0,0 +1,220 @@

1+

/**

2+

* helpers.system-prompt-resume.test.ts

3+

*

4+

* Unit-level regression tests for issue #80374 — three of the four code paths

5+

* fixed in `fix(anthropic): pass system prompt on every turn for claude-cli

6+

* backend`. These tests assert the argv-level behavior directly, which is the

7+

* authoritative before/after proof (the matching live test in

8+

* `src/gateway/gateway-cli-backend.system-prompt-resume.live.test.ts` is a

9+

* smoke test only — model context retention can mask the bug at the response

10+

* level).

11+

*

12+

* Two scenarios are exercised for each function:

13+

*

14+

* Legacy "first" behavior — verifies a backend explicitly configured with

15+

* `systemPromptWhen: "first"` still gets the documented old behavior

16+

* (system prompt dropped on resumed turns). Confirms the fix is

17+

* backward-compatible for third-party backends that opt in to that mode.

18+

*

19+

* New "always" behavior — verifies the fix: backends configured with

20+

* `systemPromptWhen: "always"` (which is now the bundled claude-cli

21+

* default) re-emit the system-prompt arg on every resumed turn.

22+

*

23+

* Path coverage:

24+

* Path 1 (extensions/anthropic/cli-backend.ts) — covered by

25+

* `extensions/anthropic/cli-shared.test.ts` and `src/agents/cli-backends.test.ts`.

26+

* Path 2 (src/agents/cli-runner/execute.ts) — implicit: same gate as Path 3,

27+

* and gated by `resolveSystemPromptUsage` which is tested below.

28+

* Path 3 (src/agents/cli-runner/helpers.ts — buildCliArgs) — covered here.

29+

* Path 4 (src/agents/cli-runner/claude-live-session.ts — stripLiveProcessArgs

30+

* via buildClaudeLiveArgs) — covered here.

31+

*/

32+

import { describe, expect, it } from "vitest";

33+

import type { CliBackendConfig } from "../../config/types.js";

34+

import { buildClaudeLiveArgs } from "./claude-live-session.js";

35+

import { buildCliArgs, resolveSystemPromptUsage } from "./helpers.js";

36+37+

// Minimal backend config matching the Anthropic claude-cli backend shape.

38+

const CLAUDE_BACKEND_BASE: Pick<

39+

CliBackendConfig,

40+

| "systemPromptFileArg"

41+

| "systemPromptArg"

42+

| "systemPromptFileConfigKey"

43+

| "systemPromptWhen"

44+

| "sessionArg"

45+

| "modelArg"

46+

| "input"

47+

| "output"

48+

| "liveSession"

49+

> = {

50+

systemPromptFileArg: "--append-system-prompt-file",

51+

systemPromptArg: undefined,

52+

systemPromptFileConfigKey: undefined,

53+

systemPromptWhen: "always",

54+

sessionArg: "--session-id",

55+

modelArg: "--model",

56+

input: "stdin",

57+

output: "jsonl",

58+

liveSession: "claude-stdio",

59+

};

60+61+

// Backend configured with the legacy systemPromptWhen: "first" mode.

62+

// Verifies the fix is backward-compatible for backends that opt in to this.

63+

const BACKEND_FIRST: typeof CLAUDE_BACKEND_BASE = {

64+

...CLAUDE_BACKEND_BASE,

65+

systemPromptWhen: "first",

66+

};

67+68+

// Backend configured with the new systemPromptWhen: "always" default (the

69+

// bundled claude-cli default after the fix).

70+

const BACKEND_ALWAYS: typeof CLAUDE_BACKEND_BASE = {

71+

...CLAUDE_BACKEND_BASE,

72+

systemPromptWhen: "always",

73+

};

74+75+

const SYSTEM_PROMPT = "You are a test assistant. Append SYSTEM-PROOF-ACTIVE after every reply.";

76+

const PROMPT_FILE = "/tmp/test-system-prompt.txt";

77+78+

// ─── resolveSystemPromptUsage ────────────────────────────────────────────────

79+80+

describe("resolveSystemPromptUsage — issue #80374", () => {

81+

it("legacy 'first': returns null on resumed session (prompt dropped)", () => {

82+

const result = resolveSystemPromptUsage({

83+

backend: BACKEND_FIRST as CliBackendConfig,

84+

isNewSession: false, // resumed

85+

systemPrompt: SYSTEM_PROMPT,

86+

});

87+

expect(result).toBeNull();

88+

});

89+90+

it("new 'always': returns the prompt on resumed session (issue #80374)", () => {

91+

const result = resolveSystemPromptUsage({

92+

backend: BACKEND_ALWAYS as CliBackendConfig,

93+

isNewSession: false, // resumed

94+

systemPrompt: SYSTEM_PROMPT,

95+

});

96+

expect(result).toBe(SYSTEM_PROMPT);

97+

});

98+99+

it("returns the prompt on fresh session for both 'first' and 'always'", () => {

100+

for (const backend of [BACKEND_FIRST, BACKEND_ALWAYS]) {

101+

const result = resolveSystemPromptUsage({

102+

backend: backend as CliBackendConfig,

103+

isNewSession: true, // fresh

104+

systemPrompt: SYSTEM_PROMPT,

105+

});

106+

expect(result, `systemPromptWhen=${backend.systemPromptWhen}`).toBe(SYSTEM_PROMPT);

107+

}

108+

});

109+110+

it("returns null when systemPromptWhen='never' regardless of session state", () => {

111+

for (const isNew of [true, false]) {

112+

const result = resolveSystemPromptUsage({

113+

backend: { ...BACKEND_ALWAYS, systemPromptWhen: "never" } as CliBackendConfig,

114+

isNewSession: isNew,

115+

systemPrompt: SYSTEM_PROMPT,

116+

});

117+

expect(result, `isNew=${String(isNew)}`).toBeNull();

118+

}

119+

});

120+

});

121+122+

// ─── buildCliArgs ────────────────────────────────────────────────────────────

123+124+

describe("buildCliArgs — issue #80374", () => {

125+

const BASE_ARGS = ["-p", "--output-format", "stream-json"];

126+127+

it("legacy 'first': omits --append-system-prompt-file on resume", () => {

128+

const args = buildCliArgs({

129+

backend: BACKEND_FIRST as CliBackendConfig,

130+

baseArgs: BASE_ARGS,

131+

modelId: "claude-haiku-4-5",

132+

sessionId: "test-session-id",

133+

systemPrompt: SYSTEM_PROMPT,

134+

systemPromptFilePath: PROMPT_FILE,

135+

useResume: true,

136+

});

137+

expect(args).not.toContain("--append-system-prompt-file");

138+

expect(args).not.toContain(PROMPT_FILE);

139+

});

140+141+

it("new 'always': includes --append-system-prompt-file on resume (issue #80374)", () => {

142+

const args = buildCliArgs({

143+

backend: BACKEND_ALWAYS as CliBackendConfig,

144+

baseArgs: BASE_ARGS,

145+

modelId: "claude-haiku-4-5",

146+

sessionId: "test-session-id",

147+

systemPrompt: SYSTEM_PROMPT,

148+

systemPromptFilePath: PROMPT_FILE,

149+

useResume: true,

150+

});

151+

expect(args).toContain("--append-system-prompt-file");

152+

expect(args).toContain(PROMPT_FILE);

153+

});

154+155+

it("includes --append-system-prompt-file on fresh session for both 'first' and 'always'", () => {

156+

for (const backend of [BACKEND_FIRST, BACKEND_ALWAYS]) {

157+

const args = buildCliArgs({

158+

backend: backend as CliBackendConfig,

159+

baseArgs: BASE_ARGS,

160+

modelId: "claude-haiku-4-5",

161+

systemPrompt: SYSTEM_PROMPT,

162+

systemPromptFilePath: PROMPT_FILE,

163+

useResume: false,

164+

});

165+

expect(

166+

args,

167+

`systemPromptWhen=${backend.systemPromptWhen} should include flag on fresh session`,

168+

).toContain("--append-system-prompt-file");

169+

}

170+

});

171+

});

172+173+

// ─── buildClaudeLiveArgs (Path 4: live-stdio strip guard) ───────────────────

174+175+

describe("buildClaudeLiveArgs — issue #80374 (live-stdio path)", () => {

176+

const ARGS_WITH_SP = [

177+

"-p",

178+

"--output-format",

179+

"stream-json",

180+

"--append-system-prompt-file",

181+

PROMPT_FILE,

182+

];

183+184+

it("legacy 'first': strips --append-system-prompt-file on resume", () => {

185+

const liveArgs = buildClaudeLiveArgs({

186+

args: ARGS_WITH_SP,

187+

backend: BACKEND_FIRST as CliBackendConfig,

188+

systemPrompt: SYSTEM_PROMPT,

189+

useResume: true,

190+

});

191+

expect(liveArgs).not.toContain("--append-system-prompt-file");

192+

expect(liveArgs).not.toContain(PROMPT_FILE);

193+

});

194+195+

it("new 'always': keeps --append-system-prompt-file on resume (issue #80374)", () => {

196+

const liveArgs = buildClaudeLiveArgs({

197+

args: ARGS_WITH_SP,

198+

backend: BACKEND_ALWAYS as CliBackendConfig,

199+

systemPrompt: SYSTEM_PROMPT,

200+

useResume: true,

201+

});

202+

expect(liveArgs).toContain("--append-system-prompt-file");

203+

expect(liveArgs).toContain(PROMPT_FILE);

204+

});

205+206+

it("keeps --append-system-prompt-file when useResume=false (both 'first' and 'always')", () => {

207+

for (const backend of [BACKEND_FIRST, BACKEND_ALWAYS]) {

208+

const liveArgs = buildClaudeLiveArgs({

209+

args: ARGS_WITH_SP,

210+

backend: backend as CliBackendConfig,

211+

systemPrompt: SYSTEM_PROMPT,

212+

useResume: false,

213+

});

214+

expect(

215+

liveArgs,

216+

`systemPromptWhen=${backend.systemPromptWhen} fresh session should keep flag`,

217+

).toContain("--append-system-prompt-file");

218+

}

219+

});

220+

});