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

IT之家
IT之家
H
Help Net Security
GbyAI
GbyAI
博客园_首页
G
Google Developers Blog
Microsoft Security Blog
Microsoft Security Blog
博客园 - 【当耐特】
月光博客
月光博客
美团技术团队
B
Blog RSS Feed
博客园 - 三生石上(FineUI控件)
WordPress大学
WordPress大学
博客园 - 叶小钗
有赞技术团队
有赞技术团队
T
The Blog of Author Tim Ferriss
Engineering at Meta
Engineering at Meta
Google DeepMind News
Google DeepMind News
Y
Y Combinator Blog
宝玉的分享
宝玉的分享
Microsoft Azure Blog
Microsoft Azure Blog
罗磊的独立博客
云风的 BLOG
云风的 BLOG
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
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
fix(heartbeat): align response tool prompts (#76458) · op...
vincentkoc · 2026-05-03 · via Recent Commits to openclaw:main

File tree

  • extensions/qa-lab/src

  • qa/scenarios

    • models

    • workspace

  • scripts/e2e/lib/codex-npm-plugin-live

  • src

    • agents/pi-embedded-runner

      • run

    • auto-reply

      • reply

    • infra

Original file line numberDiff line numberDiff line change

@@ -95,6 +95,7 @@ Docs: https://docs.openclaw.ai

9595

- Gateway: preserve stack diagnostics when `chat.send` or agent attachment parsing/staging fails, improving image-send failure triage. Refs #63432. (#75135) Thanks @keen0206.

9696

- Agents/idle-timeout: add a cost-runaway breaker to the outer embedded-run retry loop that halts further attempts after 5 consecutive idle timeouts without completed model progress, so a wedged provider can no longer fan paid model calls out across the same run; completed text or tool-call progress resets the breaker, but partial tool-argument token dribbles do not. Fixes #76293. Thanks @ThePuma312.

9797

- Heartbeats/Codex: stop sending the legacy `HEARTBEAT_OK` prompt instruction when heartbeat turns have the structured `heartbeat_respond` tool, while keeping the text sentinel for legacy automatic heartbeat replies. Thanks @pashpashpash.

98+

- Heartbeats/Codex: keep structured heartbeat prompts aligned with actual `heartbeat_respond` tool availability and keep tool-disabled commitment check-ins on the legacy ack path. Thanks @pashpashpash and @vincentkoc.

9899

- Agent runtimes: fail explicit plugin runtime selections honestly when the requested harness is unavailable instead of silently falling back to the embedded PI runtime. Thanks @pashpashpash.

99100

- Maintainer workflow: push prepared PR heads through GitHub's verified commit API by default and require an explicit override before git-protocol pushes can publish unsigned commits. Thanks @BunsDev.

100101

- Feishu: resolve setup/status probes through the selected/default account so multi-account configs with account-scoped app credentials show as configured and probeable. Fixes #72930. Thanks @brokemac79.

Original file line numberDiff line numberDiff line change

@@ -53,7 +53,6 @@ describe("qa scenario catalog", () => {

5353

const codexLeakConfig = readQaScenarioExecutionConfig("codex-harness-no-meta-leak") as

5454

| {

5555

harnessRuntime?: string;

56-

harnessFallback?: string;

5756

expectedReply?: string;

5857

forbiddenReplySubstrings?: string[];

5958

}

@@ -73,7 +72,6 @@ describe("qa scenario catalog", () => {

7372

);

7473

expect(codexLeak.title).toBe("Codex harness no meta leak");

7574

expect(codexLeakConfig?.harnessRuntime).toBe("codex");

76-

expect(codexLeakConfig?.harnessFallback).toBe("none");

7775

expect(JSON.stringify(codexLeak.execution.flow)).toContain("agentRuntime");

7876

expect(JSON.stringify(codexLeak.execution.flow)).not.toContain("embeddedHarness");

7977

expect(codexLeakConfig?.expectedReply).toBe("QA_LEAK_OK");

Original file line numberDiff line numberDiff line change

@@ -11,7 +11,7 @@ coverage:

1111

- runtime.no-meta-leak

1212

objective: Verify the Codex app-server harness keeps coordination/meta chatter out of the visible reply.

1313

successCriteria:

14-

- The scenario forces the Codex embedded harness and disables PI fallback.

14+

- The scenario forces the Codex embedded harness.

1515

- The final visible reply includes the requested confirmation token.

1616

- The visible reply does not include internal coordination or progress chatter.

1717

docsRefs:

@@ -29,7 +29,6 @@ execution:

2929

requiredProvider: codex

3030

requiredModel: gpt-5.5

3131

harnessRuntime: codex

32-

harnessFallback: none

3332

expectedReply: QA_LEAK_OK

3433

prompt: |-

3534

Think through your answer privately, but do not expose any internal planning, thread-context checks, or progress narration.

@@ -76,8 +75,6 @@ steps:

7675

agentRuntime:

7776

id:

7877

expr: config.harnessRuntime

79-

fallback:

80-

expr: config.harnessFallback

8178

- call: waitForGatewayHealthy

8279

args:

8380

- ref: env

@@ -94,11 +91,7 @@ steps:

9491

expr: "snapshot.config.agents?.defaults?.agentRuntime?.id === config.harnessRuntime"

9592

message:

9693

expr: "`expected agentRuntime.id=${config.harnessRuntime}, got ${JSON.stringify(snapshot.config.agents?.defaults?.agentRuntime)}`"

97-

- assert:

98-

expr: "snapshot.config.agents?.defaults?.agentRuntime?.fallback === config.harnessFallback"

99-

message:

100-

expr: "`expected agentRuntime.fallback=${config.harnessFallback}, got ${JSON.stringify(snapshot.config.agents?.defaults?.agentRuntime)}`"

101-

detailsExpr: "env.providerMode === 'live-frontier' ? `provider=${selected?.provider} model=${selected?.model} runtime=${snapshot.config.agents?.defaults?.agentRuntime?.id} fallback=${snapshot.config.agents?.defaults?.agentRuntime?.fallback}` : `mock mode: parsed ${scenario.id}`"

94+

detailsExpr: "env.providerMode === 'live-frontier' ? `provider=${selected?.provider} model=${selected?.model} runtime=${snapshot.config.agents?.defaults?.agentRuntime?.id}` : `mock mode: parsed ${scenario.id}`"

10295

- name: keeps codex coordination chatter out of the visible reply

10396

actions:

10497

- if:

Original file line numberDiff line numberDiff line change

@@ -12,7 +12,7 @@ coverage:

1212

objective: Verify the Codex app-server harness can plan and build a medium-complex self-contained browser game.

1313

successCriteria:

1414

- A live-frontier run fails fast unless the selected primary model is openai/gpt-5.5 with the Codex harness forced.

15-

- The scenario forces the Codex embedded harness and disables PI fallback.

15+

- The scenario forces the Codex embedded harness.

1616

- The prompt explicitly asks the agent to enter plan mode before editing.

1717

- The agent writes a self-contained HTML game with a canvas loop, controls, scoring, waves, pause, and restart.

1818

docsRefs:

@@ -30,7 +30,6 @@ execution:

3030

requiredProvider: codex

3131

requiredModel: gpt-5.5

3232

harnessRuntime: codex

33-

harnessFallback: none

3433

artifactFile: star-garden-defenders-codex.html

3534

gameTitle: Star Garden Defenders

3635

minBytes: 5000

@@ -81,8 +80,6 @@ steps:

8180

agentRuntime:

8281

id:

8382

expr: config.harnessRuntime

84-

fallback:

85-

expr: config.harnessFallback

8683

- call: waitForGatewayHealthy

8784

args:

8885

- ref: env

@@ -99,11 +96,7 @@ steps:

9996

expr: "snapshot.config.agents?.defaults?.agentRuntime?.id === config.harnessRuntime"

10097

message:

10198

expr: "`expected agentRuntime.id=${config.harnessRuntime}, got ${JSON.stringify(snapshot.config.agents?.defaults?.agentRuntime)}`"

102-

- assert:

103-

expr: "snapshot.config.agents?.defaults?.agentRuntime?.fallback === config.harnessFallback"

104-

message:

105-

expr: "`expected agentRuntime.fallback=${config.harnessFallback}, got ${JSON.stringify(snapshot.config.agents?.defaults?.agentRuntime)}`"

106-

detailsExpr: "env.providerMode === 'live-frontier' ? `provider=${selected?.provider} model=${selected?.model} runtime=${snapshot.config.agents?.defaults?.agentRuntime?.id} fallback=${snapshot.config.agents?.defaults?.agentRuntime?.fallback}` : `mock mode: parsed ${scenario.id}`"

99+

detailsExpr: "env.providerMode === 'live-frontier' ? `provider=${selected?.provider} model=${selected?.model} runtime=${snapshot.config.agents?.defaults?.agentRuntime?.id}` : `mock mode: parsed ${scenario.id}`"

107100

- name: builds the medium game artifact

108101

actions:

109102

- if:

Original file line numberDiff line numberDiff line change

@@ -30,7 +30,6 @@ execution:

3030

requiredProvider: openai

3131

requiredModel: gpt-5.5

3232

harnessRuntime: pi

33-

harnessFallback: pi

3433

artifactFile: star-garden-defenders-pi.html

3534

gameTitle: Star Garden Defenders

3635

minBytes: 5000

@@ -81,8 +80,6 @@ steps:

8180

agentRuntime:

8281

id:

8382

expr: config.harnessRuntime

84-

fallback:

85-

expr: config.harnessFallback

8683

- call: waitForGatewayHealthy

8784

args:

8885

- ref: env

Original file line numberDiff line numberDiff line change

@@ -66,7 +66,7 @@ function configure() {

6666

defaults: {

6767

...cfg.agents?.defaults,

6868

model: { primary: modelRef, fallbacks: [] },

69-

agentRuntime: { id: "codex", fallback: "none" },

69+

agentRuntime: { id: "codex" },

7070

workspace: path.join(state, "workspace"),

7171

skipBootstrap: true,

7272

timeoutSeconds: 420,

Original file line numberDiff line numberDiff line change

@@ -1162,6 +1162,8 @@ export async function runEmbeddedPiAgent(

11621162

ownerOnlyToolAllowlist: params.ownerOnlyToolAllowlist,

11631163

disableMessageTool: params.disableMessageTool,

11641164

forceMessageTool: params.forceMessageTool,

1165+

enableHeartbeatTool: params.enableHeartbeatTool,

1166+

forceHeartbeatTool: params.forceHeartbeatTool,

11651167

requireExplicitMessageTarget: params.requireExplicitMessageTarget,

11661168

internalEvents: params.internalEvents,

11671169

bootstrapPromptWarningSignaturesSeen,

Original file line numberDiff line numberDiff line change

@@ -925,6 +925,8 @@ export async function runEmbeddedAttempt(

925925

params.requireExplicitMessageTarget ?? isSubagentSessionKey(params.sessionKey),

926926

disableMessageTool: params.disableMessageTool,

927927

forceMessageTool: params.forceMessageTool,

928+

enableHeartbeatTool: params.enableHeartbeatTool,

929+

forceHeartbeatTool: params.forceHeartbeatTool,

928930

authProfileStore: params.authProfileStore,

929931

recordToolPrepStage: (name) => corePluginToolStages.mark(name),

930932

onYield: (message) => {

Original file line numberDiff line numberDiff line change

@@ -94,6 +94,10 @@ export type RunEmbeddedPiAgentParams = {

9494

promptMode?: PromptMode;

9595

/** Keep the message tool available even when a narrow profile would omit it. */

9696

forceMessageTool?: boolean;

97+

/** Include the heartbeat response tool for structured heartbeat outcomes. */

98+

enableHeartbeatTool?: boolean;

99+

/** Keep the heartbeat response tool available even when a narrow profile would omit it. */

100+

forceHeartbeatTool?: boolean;

97101

/** Allow runtime plugins for this run to late-bind the gateway subagent. */

98102

allowGatewaySubagentBinding?: boolean;

99103

sessionFile: string;

Original file line numberDiff line numberDiff line change

@@ -59,6 +59,10 @@ export type GetReplyOptions = {

5959

suppressToolErrorWarnings?: boolean;

6060

/** If true, run the model without OpenClaw tools for this turn. */

6161

disableTools?: boolean;

62+

/** If true, include the heartbeat response tool for structured heartbeat outcomes. */

63+

enableHeartbeatTool?: boolean;

64+

/** If true, keep the heartbeat response tool available even under narrow tool profiles. */

65+

forceHeartbeatTool?: boolean;

6266

/**

6367

* If true, dispatch skips default tool/progress text messages and expects the

6468

* channel to surface progress via its own streaming/edit UX.