feat: 增强 auto mode 的易用性 (#312)

* feat: poor 模式降级 yolo 审阅模型

* feat: 为多模块添加 Langfuse tracing 支持

在 web search、agent creation、away summary、token estimation、
skill improvement 等模块中集成 Langfuse trace,并透传至
compact/apiQueryHook/execPromptHook 等调用链。

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix: 让 auto mode 记录回主 trace

* fix: reopen auto mode prompt when classifier is unavailable

* fix: 修复 auto mode 情况下, llm 报错导致弹窗也不打开的问题

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
claude-code-best
2026-04-20 21:13:09 +08:00
committed by GitHub
parent e4ce08fe39
commit ed4bdb9338
18 changed files with 281 additions and 145 deletions

View File

@@ -1,153 +1,136 @@
import { mock, describe, expect, test } from "bun:test";
import { mock, describe, expect, test } from 'bun:test'
import { createFileStateCacheWithSizeLimit } from '../../../utils/fileStateCache.js'
import { createSubagentContext } from '../../../utils/forkedAgent.js'
import { getEmptyToolPermissionContext } from '../../../Tool.js'
// Mock log.ts to cut the heavy dependency chain
mock.module("src/utils/log.ts", () => ({
mock.module('src/utils/log.ts', () => ({
logError: () => {},
logToFile: () => {},
getLogDisplayTitle: () => "",
getLogDisplayTitle: () => '',
logEvent: () => {},
logMCPError: () => {},
logMCPDebug: () => {},
dateToFilename: (d: Date) => d.toISOString().replace(/[:.]/g, "-"),
getLogFilePath: () => "/tmp/mock-log",
dateToFilename: (d: Date) => d.toISOString().replace(/[:.]/g, '-'),
getLogFilePath: () => '/tmp/mock-log',
attachErrorLogSink: () => {},
getInMemoryErrors: () => [],
loadErrorLogs: async () => [],
getErrorLogByIndex: async () => null,
captureAPIRequest: () => {},
_resetErrorLogForTesting: () => {},
}));
}))
const {
getDenyRuleForTool,
getAskRuleForTool,
getDenyRuleForAgent,
filterDeniedAgents,
} = await import("../permissions");
} = await import('../permissions')
import { getEmptyToolPermissionContext } from "../../../Tool";
// ─── Helper ─────────────────────────────────────────────────────────────
function makeContext(opts: {
denyRules?: string[];
askRules?: string[];
}) {
const ctx = getEmptyToolPermissionContext();
const deny: Record<string, string[]> = {};
const ask: Record<string, string[]> = {};
// alwaysDenyRules stores raw rule strings — getDenyRules() calls
// permissionRuleValueFromString internally
if (opts.denyRules?.length) {
deny["localSettings"] = opts.denyRules;
}
if (opts.askRules?.length) {
ask["localSettings"] = opts.askRules;
}
return {
...ctx,
alwaysDenyRules: deny,
alwaysAskRules: ask,
} as any;
function makeContext(opts: { denyRules?: string[]; askRules?: string[] }) {
const ctx = getEmptyToolPermissionContext()
const deny: Record<string, string[]> = {}
const ask: Record<string, string[]> = {}
if (opts.denyRules?.length) deny.localSettings = opts.denyRules
if (opts.askRules?.length) ask.localSettings = opts.askRules
return { ...ctx, alwaysDenyRules: deny, alwaysAskRules: ask } as any
}
function makeTool(name: string, mcpInfo?: { serverName: string; toolName: string }) {
return { name, mcpInfo };
return { name, mcpInfo }
}
// ─── getDenyRuleForTool ─────────────────────────────────────────────────
describe('getDenyRuleForTool', () => {
test('returns null when no deny rules', () => {
const ctx = makeContext({})
expect(getDenyRuleForTool(ctx, makeTool('Bash'))).toBeNull()
})
test('returns matching deny rule for tool', () => {
const ctx = makeContext({ denyRules: ['Bash'] })
const result = getDenyRuleForTool(ctx, makeTool('Bash'))
expect(result).not.toBeNull()
expect(result!.ruleValue.toolName).toBe('Bash')
})
test('returns null for non-matching tool', () => {
const ctx = makeContext({ denyRules: ['Bash'] })
expect(getDenyRuleForTool(ctx, makeTool('Read'))).toBeNull()
})
test('rule with content does not match whole-tool deny', () => {
const ctx = makeContext({ denyRules: ['Bash(rm -rf)'] })
const result = getDenyRuleForTool(ctx, makeTool('Bash'))
expect(result).toBeNull()
})
})
describe("getDenyRuleForTool", () => {
test("returns null when no deny rules", () => {
const ctx = makeContext({});
expect(getDenyRuleForTool(ctx, makeTool("Bash"))).toBeNull();
});
describe('getAskRuleForTool', () => {
test('returns null when no ask rules', () => {
const ctx = makeContext({})
expect(getAskRuleForTool(ctx, makeTool('Bash'))).toBeNull()
})
test('returns matching ask rule', () => {
const ctx = makeContext({ askRules: ['Write'] })
const result = getAskRuleForTool(ctx, makeTool('Write'))
expect(result).not.toBeNull()
})
test('returns null for non-matching tool', () => {
const ctx = makeContext({ askRules: ['Write'] })
expect(getAskRuleForTool(ctx, makeTool('Bash'))).toBeNull()
})
})
test("returns matching deny rule for tool", () => {
const ctx = makeContext({ denyRules: ["Bash"] });
const result = getDenyRuleForTool(ctx, makeTool("Bash"));
expect(result).not.toBeNull();
expect(result!.ruleValue.toolName).toBe("Bash");
});
describe('getDenyRuleForAgent', () => {
test('returns null when no deny rules', () => {
const ctx = makeContext({})
expect(getDenyRuleForAgent(ctx, 'Agent', 'Explore')).toBeNull()
})
test('returns matching deny rule for agent type', () => {
const ctx = makeContext({ denyRules: ['Agent(Explore)'] })
const result = getDenyRuleForAgent(ctx, 'Agent', 'Explore')
expect(result).not.toBeNull()
})
test('returns null for non-matching agent type', () => {
const ctx = makeContext({ denyRules: ['Agent(Explore)'] })
expect(getDenyRuleForAgent(ctx, 'Agent', 'Research')).toBeNull()
})
})
test("returns null for non-matching tool", () => {
const ctx = makeContext({ denyRules: ["Bash"] });
expect(getDenyRuleForTool(ctx, makeTool("Read"))).toBeNull();
});
describe('Langfuse trace propagation', () => {
test('subagent context preserves parent trace for nested side queries', () => {
const parentTrace = { id: 'parent-trace' } as never
const parentContext = {
...getEmptyToolPermissionContext(),
messages: [],
abortController: new AbortController(),
readFileState: createFileStateCacheWithSizeLimit(1),
getAppState: () => ({ toolPermissionContext: getEmptyToolPermissionContext() }),
setAppState: () => {},
updateFileHistoryState: () => {},
updateAttributionState: () => {},
setInProgressToolUseIDs: () => {},
setResponseLength: () => {},
langfuseTrace: parentTrace,
} as never
const subagentContext = createSubagentContext(parentContext)
expect(subagentContext.langfuseRootTrace).toBe(parentTrace)
})
})
test("rule with content does not match whole-tool deny", () => {
// getDenyRuleForTool uses toolMatchesRule which requires ruleContent === undefined
// Rules like "Bash(rm -rf)" only match specific invocations, not the entire tool
const ctx = makeContext({ denyRules: ["Bash(rm -rf)"] });
const result = getDenyRuleForTool(ctx, makeTool("Bash"));
expect(result).toBeNull();
});
});
// ─── getAskRuleForTool ──────────────────────────────────────────────────
describe("getAskRuleForTool", () => {
test("returns null when no ask rules", () => {
const ctx = makeContext({});
expect(getAskRuleForTool(ctx, makeTool("Bash"))).toBeNull();
});
test("returns matching ask rule", () => {
const ctx = makeContext({ askRules: ["Write"] });
const result = getAskRuleForTool(ctx, makeTool("Write"));
expect(result).not.toBeNull();
});
test("returns null for non-matching tool", () => {
const ctx = makeContext({ askRules: ["Write"] });
expect(getAskRuleForTool(ctx, makeTool("Bash"))).toBeNull();
});
});
// ─── getDenyRuleForAgent ────────────────────────────────────────────────
describe("getDenyRuleForAgent", () => {
test("returns null when no deny rules", () => {
const ctx = makeContext({});
expect(getDenyRuleForAgent(ctx, "Agent", "Explore")).toBeNull();
});
test("returns matching deny rule for agent type", () => {
const ctx = makeContext({ denyRules: ["Agent(Explore)"] });
const result = getDenyRuleForAgent(ctx, "Agent", "Explore");
expect(result).not.toBeNull();
});
test("returns null for non-matching agent type", () => {
const ctx = makeContext({ denyRules: ["Agent(Explore)"] });
expect(getDenyRuleForAgent(ctx, "Agent", "Research")).toBeNull();
});
});
// ─── filterDeniedAgents ─────────────────────────────────────────────────
describe("filterDeniedAgents", () => {
test("returns all agents when no deny rules", () => {
const ctx = makeContext({});
const agents = [{ agentType: "Explore" }, { agentType: "Research" }];
expect(filterDeniedAgents(agents, ctx, "Agent")).toEqual(agents);
});
test("filters out denied agent type", () => {
const ctx = makeContext({ denyRules: ["Agent(Explore)"] });
const agents = [{ agentType: "Explore" }, { agentType: "Research" }];
const result = filterDeniedAgents(agents, ctx, "Agent");
expect(result).toHaveLength(1);
expect(result[0]!.agentType).toBe("Research");
});
test("returns empty array when all agents denied", () => {
const ctx = makeContext({
denyRules: ["Agent(Explore)", "Agent(Research)"],
});
const agents = [{ agentType: "Explore" }, { agentType: "Research" }];
expect(filterDeniedAgents(agents, ctx, "Agent")).toEqual([]);
});
});
describe('filterDeniedAgents', () => {
test('returns all agents when no deny rules', () => {
const ctx = makeContext({})
const agents = [{ agentType: 'Explore' }, { agentType: 'Research' }]
expect(filterDeniedAgents(agents, ctx, 'Agent')).toEqual(agents)
})
test('filters out denied agent type', () => {
const ctx = makeContext({ denyRules: ['Agent(Explore)'] })
const agents = [{ agentType: 'Explore' }, { agentType: 'Research' }]
const result = filterDeniedAgents(agents, ctx, 'Agent')
expect(result).toHaveLength(1)
expect(result[0]!.agentType).toBe('Research')
})
test('returns empty array when all agents denied', () => {
const ctx = makeContext({ denyRules: ['Agent(Explore)', 'Agent(Research)'] })
const agents = [{ agentType: 'Explore' }, { agentType: 'Research' }]
expect(filterDeniedAgents(agents, ctx, 'Agent')).toEqual([])
})
})

View File

@@ -7,7 +7,8 @@ import { logForDebugging } from '../debug.js'
import { errorMessage } from '../errors.js'
import { lazySchema } from '../lazySchema.js'
import { logError } from '../log.js'
import { getMainLoopModel } from '../model/model.js'
import { getMainLoopModel, getSmallFastModel } from '../model/model.js'
import { isPoorModeActive } from '../../commands/poor/poorMode.js'
import { sideQuery } from '../sideQuery.js'
import { jsonStringify } from '../slowOperations.js'
@@ -172,7 +173,7 @@ ${conversationContext ? `\nRecent conversation context:\n${conversationContext}`
Explain this command in context.`
const model = getMainLoopModel()
const model = isPoorModeActive() ? getSmallFastModel() : getMainLoopModel()
// Use sideQuery with forced tool choice for guaranteed structured output
const response = await sideQuery({

View File

@@ -690,13 +690,16 @@ export const hasPermissionsToUseTool: CanUseToolFn = async (
setClassifierChecking(toolUseID)
let classifierResult
try {
logForDebugging(
`[auto-mode] classifyYoloAction called with langfuseTrace=${context.langfuseTrace ? `id=${(context.langfuseTrace as unknown as Record<string, unknown>).id ?? 'present'}` : 'null/undefined'}`,
)
classifierResult = await classifyYoloAction(
context.messages,
action,
context.options.tools,
appState.toolPermissionContext,
context.abortController.signal,
context.langfuseTrace,
context.langfuseRootTrace ?? context.langfuseTrace,
)
} finally {
clearClassifierChecking(toolUseID)
@@ -851,12 +854,30 @@ export const hasPermissionsToUseTool: CanUseToolFn = async (
CLASSIFIER_FAIL_CLOSED_REFRESH_MS,
)
) {
if (appState.toolPermissionContext.shouldAvoidPermissionPrompts) {
logForDebugging(
'Auto mode classifier unavailable, denying with retry guidance (fail closed)',
{ level: 'warn' },
)
return {
behavior: 'deny',
decisionReason: {
type: 'classifier',
classifier: 'auto-mode',
reason: 'Classifier unavailable',
},
message: buildClassifierUnavailableMessage(
tool.name,
classifierResult.model,
),
}
}
logForDebugging(
'Auto mode classifier unavailable, denying with retry guidance (fail closed)',
'Auto mode classifier unavailable, falling back to prompting with retry guidance (fail closed)',
{ level: 'warn' },
)
return {
behavior: 'deny',
behavior: 'ask',
decisionReason: {
type: 'classifier',
classifier: 'auto-mode',

View File

@@ -28,7 +28,8 @@ import { errorMessage } from '../errors.js'
import { lazySchema } from '../lazySchema.js'
import { extractTextContent } from '../messages.js'
import { resolveAntModel } from '../model/antModels.js'
import { getMainLoopModel } from '../model/model.js'
import { getDefaultSonnetModel, getMainLoopModel } from '../model/model.js'
import { isPoorModeActive } from '../../commands/poor/poorMode.js'
import { getAutoModeConfig } from '../settings/settings.js'
import { sideQuery } from '../sideQuery.js'
import type { LangfuseSpan } from '../../services/langfuse/index.js'
@@ -1350,6 +1351,10 @@ function getClassifierModel(): string {
if (config?.model) {
return config.model
}
// Poor mode: downgrade classifier to Sonnet to reduce cost
if (isPoorModeActive()) {
return getDefaultSonnetModel()
}
return getMainLoopModel()
}