fix: strip cache_control fields from content blocks (#189)
Claude Code CLI sends cache_control on text, thinking, tool_use, and tool_result blocks for prompt caching. Cloud Code API rejects these with "Extra inputs are not permitted". - Add cleanCacheControl() to proactively strip cache_control at pipeline entry - Add sanitizeTextBlock() and sanitizeToolUseBlock() for defense-in-depth - Update reorderAssistantContent() to use block sanitizers - Add test-cache-control.cjs with multi-model test coverage - Update frontend dashboard tests to match current UI design - Update strategy tests to match v2.4.0 fallback behavior - Update CLAUDE.md and README.md with recent features Inspired by Antigravity-Manager's clean_cache_control_from_messages() pattern. Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
Badri Narayanan S
@@ -91,11 +91,12 @@ const tests = [
|
||||
const res = await request('/views/dashboard.html');
|
||||
const html = res.data;
|
||||
|
||||
// Dashboard uses dropdown-based filters for time range, display mode, and model selection
|
||||
const filterElements = [
|
||||
'filters.account', // Account filter
|
||||
'filters.family', // Model family filter
|
||||
'filters.search', // Search input
|
||||
'computeQuotaRows' // Filter action
|
||||
'showTimeRangeDropdown', // Time range dropdown toggle
|
||||
'showDisplayModeDropdown', // Display mode dropdown toggle
|
||||
'showModelFilter', // Model/family filter dropdown toggle
|
||||
'setTimeRange' // Time range action
|
||||
];
|
||||
|
||||
const missing = filterElements.filter(el => !html.includes(el));
|
||||
@@ -106,23 +107,24 @@ const tests = [
|
||||
}
|
||||
},
|
||||
{
|
||||
name: 'Dashboard table has required columns',
|
||||
name: 'Dashboard has chart and visualization elements',
|
||||
async run() {
|
||||
const res = await request('/views/dashboard.html');
|
||||
const html = res.data;
|
||||
|
||||
const columns = [
|
||||
'modelIdentity', // Model name column
|
||||
'globalQuota', // Quota column
|
||||
'nextReset', // Reset time column
|
||||
'distribution' // Account distribution column
|
||||
// Dashboard now uses charts instead of tables
|
||||
const visualElements = [
|
||||
'quotaChart', // Quota distribution pie chart
|
||||
'usageTrendChart', // Usage trend line chart
|
||||
'usageStats.total', // Total usage stat
|
||||
'selectedFamilies' // Family selection for chart
|
||||
];
|
||||
|
||||
const missing = columns.filter(col => !html.includes(col));
|
||||
const missing = visualElements.filter(col => !html.includes(col));
|
||||
if (missing.length > 0) {
|
||||
throw new Error(`Missing table columns: ${missing.join(', ')}`);
|
||||
throw new Error(`Missing visualization elements: ${missing.join(', ')}`);
|
||||
}
|
||||
return 'All table columns present';
|
||||
return 'All chart and visualization elements present';
|
||||
}
|
||||
}
|
||||
];
|
||||
|
||||
@@ -10,6 +10,7 @@ const path = require('path');
|
||||
|
||||
const tests = [
|
||||
{ name: 'Account Selection Strategies', file: 'test-strategies.cjs' },
|
||||
{ name: 'Cache Control Stripping', file: 'test-cache-control.cjs' },
|
||||
{ name: 'Thinking Signatures', file: 'test-thinking-signatures.cjs' },
|
||||
{ name: 'Multi-turn Tools (Non-Streaming)', file: 'test-multiturn-thinking-tools.cjs' },
|
||||
{ name: 'Multi-turn Tools (Streaming)', file: 'test-multiturn-thinking-tools-streaming.cjs' },
|
||||
|
||||
297
tests/test-cache-control.cjs
Normal file
297
tests/test-cache-control.cjs
Normal file
@@ -0,0 +1,297 @@
|
||||
/**
|
||||
* Cache Control Field Test (Issue #189)
|
||||
*
|
||||
* Tests that cache_control fields on content blocks are properly stripped
|
||||
* before being sent to the Cloud Code API.
|
||||
*
|
||||
* Claude Code CLI sends cache_control on text, thinking, tool_use, tool_result,
|
||||
* image, and document blocks for prompt caching optimization. The Cloud Code API
|
||||
* rejects these with "Extra inputs are not permitted".
|
||||
*
|
||||
* This test verifies that:
|
||||
* 1. Text blocks with cache_control work correctly
|
||||
* 2. Multi-turn conversations with cache_control on assistant content work
|
||||
* 3. Tool_result blocks with cache_control work correctly
|
||||
*
|
||||
* Runs for both Claude and Gemini model families.
|
||||
*/
|
||||
const { streamRequest, analyzeContent, commonTools } = require('./helpers/http-client.cjs');
|
||||
const { getTestModels, getModelConfig } = require('./helpers/test-models.cjs');
|
||||
|
||||
const tools = [commonTools.getWeather];
|
||||
|
||||
async function runTestsForModel(family, model) {
|
||||
console.log('='.repeat(60));
|
||||
console.log(`CACHE CONTROL TEST [${family.toUpperCase()}]`);
|
||||
console.log(`Model: ${model}`);
|
||||
console.log('Tests that cache_control fields are stripped from all block types');
|
||||
console.log('='.repeat(60));
|
||||
console.log('');
|
||||
|
||||
let allPassed = true;
|
||||
const results = [];
|
||||
const modelConfig = getModelConfig(family);
|
||||
|
||||
// ===== TEST 1: User text block with cache_control =====
|
||||
console.log('TEST 1: User text block with cache_control');
|
||||
console.log('-'.repeat(40));
|
||||
|
||||
try {
|
||||
const test1Result = await streamRequest({
|
||||
model,
|
||||
max_tokens: modelConfig.max_tokens,
|
||||
stream: true,
|
||||
thinking: modelConfig.thinking,
|
||||
messages: [
|
||||
{
|
||||
role: 'user',
|
||||
content: [
|
||||
{
|
||||
type: 'text',
|
||||
text: 'What is the capital of France? Reply in one word.',
|
||||
cache_control: { type: 'ephemeral' }
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
});
|
||||
|
||||
const hasError1 = test1Result.events.some(e => e.type === 'error');
|
||||
const errorMsg1 = hasError1
|
||||
? test1Result.events.find(e => e.type === 'error')?.data?.error?.message
|
||||
: null;
|
||||
|
||||
console.log(` Response received: ${test1Result.content.length > 0 ? 'YES' : 'NO'}`);
|
||||
console.log(` Has error: ${hasError1 ? 'YES' : 'NO'}`);
|
||||
if (hasError1) {
|
||||
console.log(` Error message: ${errorMsg1}`);
|
||||
}
|
||||
|
||||
const content1 = analyzeContent(test1Result.content);
|
||||
if (content1.hasText) {
|
||||
console.log(` Response preview: "${content1.text[0].text.substring(0, 50)}..."`);
|
||||
}
|
||||
|
||||
const test1Pass = !hasError1 && test1Result.content.length > 0;
|
||||
results.push({ name: 'User text block with cache_control', passed: test1Pass });
|
||||
console.log(` Result: ${test1Pass ? 'PASS' : 'FAIL'}`);
|
||||
if (!test1Pass) allPassed = false;
|
||||
} catch (err) {
|
||||
console.log(` ERROR: ${err.message}`);
|
||||
results.push({ name: 'User text block with cache_control', passed: false });
|
||||
allPassed = false;
|
||||
}
|
||||
|
||||
// ===== TEST 2: Multi-turn with cache_control on assistant content =====
|
||||
console.log('\nTEST 2: Multi-turn with cache_control on assistant content');
|
||||
console.log('-'.repeat(40));
|
||||
|
||||
try {
|
||||
// First turn - get a response
|
||||
const turn1 = await streamRequest({
|
||||
model,
|
||||
max_tokens: modelConfig.max_tokens,
|
||||
stream: true,
|
||||
thinking: modelConfig.thinking,
|
||||
messages: [
|
||||
{ role: 'user', content: 'Say hello.' }
|
||||
]
|
||||
});
|
||||
|
||||
if (turn1.content.length === 0) {
|
||||
console.log(' SKIPPED - Turn 1 returned empty response');
|
||||
results.push({ name: 'Multi-turn with cache_control', passed: false, skipped: true });
|
||||
} else {
|
||||
// Add cache_control to ALL blocks in assistant response (simulating Claude Code)
|
||||
const modifiedContent = turn1.content.map(block => ({
|
||||
...block,
|
||||
cache_control: { type: 'ephemeral' }
|
||||
}));
|
||||
|
||||
// Second turn - use modified content with cache_control
|
||||
const turn2 = await streamRequest({
|
||||
model,
|
||||
max_tokens: modelConfig.max_tokens,
|
||||
stream: true,
|
||||
thinking: modelConfig.thinking,
|
||||
messages: [
|
||||
{ role: 'user', content: 'Say hello.' },
|
||||
{ role: 'assistant', content: modifiedContent },
|
||||
{
|
||||
role: 'user',
|
||||
content: [
|
||||
{
|
||||
type: 'text',
|
||||
text: 'Now say goodbye.',
|
||||
cache_control: { type: 'ephemeral' }
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
});
|
||||
|
||||
const hasError2 = turn2.events.some(e => e.type === 'error');
|
||||
const errorMsg2 = hasError2
|
||||
? turn2.events.find(e => e.type === 'error')?.data?.error?.message
|
||||
: null;
|
||||
|
||||
console.log(` Turn 1 blocks: ${turn1.content.length}`);
|
||||
console.log(` Turn 2 response received: ${turn2.content.length > 0 ? 'YES' : 'NO'}`);
|
||||
console.log(` Has error: ${hasError2 ? 'YES' : 'NO'}`);
|
||||
if (hasError2) {
|
||||
console.log(` Error message: ${errorMsg2}`);
|
||||
// Check specifically for cache_control error
|
||||
if (errorMsg2 && errorMsg2.includes('cache_control')) {
|
||||
console.log(' >>> cache_control field NOT stripped properly! <<<');
|
||||
}
|
||||
}
|
||||
|
||||
const content2 = analyzeContent(turn2.content);
|
||||
if (content2.hasText) {
|
||||
console.log(` Response preview: "${content2.text[0].text.substring(0, 50)}..."`);
|
||||
}
|
||||
|
||||
const test2Pass = !hasError2 && turn2.content.length > 0;
|
||||
results.push({ name: 'Multi-turn with cache_control', passed: test2Pass });
|
||||
console.log(` Result: ${test2Pass ? 'PASS' : 'FAIL'}`);
|
||||
if (!test2Pass) allPassed = false;
|
||||
}
|
||||
} catch (err) {
|
||||
console.log(` ERROR: ${err.message}`);
|
||||
results.push({ name: 'Multi-turn with cache_control', passed: false });
|
||||
allPassed = false;
|
||||
}
|
||||
|
||||
// ===== TEST 3: Tool loop with cache_control on tool_result =====
|
||||
console.log('\nTEST 3: Tool loop with cache_control on tool_result');
|
||||
console.log('-'.repeat(40));
|
||||
|
||||
try {
|
||||
// First turn - request tool use
|
||||
const toolTurn1 = await streamRequest({
|
||||
model,
|
||||
max_tokens: modelConfig.max_tokens,
|
||||
stream: true,
|
||||
tools,
|
||||
thinking: modelConfig.thinking,
|
||||
messages: [
|
||||
{ role: 'user', content: 'What is the weather in Tokyo? Use the get_weather tool.' }
|
||||
]
|
||||
});
|
||||
|
||||
const content3a = analyzeContent(toolTurn1.content);
|
||||
|
||||
if (!content3a.hasToolUse) {
|
||||
console.log(' SKIPPED - Model did not use tool in turn 1');
|
||||
results.push({ name: 'Tool_result with cache_control', passed: true, skipped: true });
|
||||
} else {
|
||||
const toolUseId = content3a.toolUse[0].id;
|
||||
console.log(` Tool use ID: ${toolUseId}`);
|
||||
|
||||
// Second turn - provide tool result with cache_control
|
||||
const toolTurn2 = await streamRequest({
|
||||
model,
|
||||
max_tokens: modelConfig.max_tokens,
|
||||
stream: true,
|
||||
tools,
|
||||
thinking: modelConfig.thinking,
|
||||
messages: [
|
||||
{ role: 'user', content: 'What is the weather in Tokyo? Use the get_weather tool.' },
|
||||
{ role: 'assistant', content: toolTurn1.content },
|
||||
{
|
||||
role: 'user',
|
||||
content: [
|
||||
{
|
||||
type: 'tool_result',
|
||||
tool_use_id: toolUseId,
|
||||
content: 'The weather in Tokyo is 22°C and partly cloudy.',
|
||||
cache_control: { type: 'ephemeral' }
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
});
|
||||
|
||||
const hasError3 = toolTurn2.events.some(e => e.type === 'error');
|
||||
const errorMsg3 = hasError3
|
||||
? toolTurn2.events.find(e => e.type === 'error')?.data?.error?.message
|
||||
: null;
|
||||
|
||||
console.log(` Turn 2 response received: ${toolTurn2.content.length > 0 ? 'YES' : 'NO'}`);
|
||||
console.log(` Has error: ${hasError3 ? 'YES' : 'NO'}`);
|
||||
if (hasError3) {
|
||||
console.log(` Error message: ${errorMsg3}`);
|
||||
if (errorMsg3 && errorMsg3.includes('cache_control')) {
|
||||
console.log(' >>> cache_control field NOT stripped properly! <<<');
|
||||
}
|
||||
}
|
||||
|
||||
const content3b = analyzeContent(toolTurn2.content);
|
||||
if (content3b.hasText) {
|
||||
console.log(` Response preview: "${content3b.text[0].text.substring(0, 50)}..."`);
|
||||
}
|
||||
|
||||
const test3Pass = !hasError3 && toolTurn2.content.length > 0;
|
||||
results.push({ name: 'Tool_result with cache_control', passed: test3Pass });
|
||||
console.log(` Result: ${test3Pass ? 'PASS' : 'FAIL'}`);
|
||||
if (!test3Pass) allPassed = false;
|
||||
}
|
||||
} catch (err) {
|
||||
console.log(` ERROR: ${err.message}`);
|
||||
results.push({ name: 'Tool_result with cache_control', passed: false });
|
||||
allPassed = false;
|
||||
}
|
||||
|
||||
// ===== Summary =====
|
||||
console.log('\n' + '='.repeat(60));
|
||||
console.log(`SUMMARY [${family.toUpperCase()}]`);
|
||||
console.log('='.repeat(60));
|
||||
|
||||
for (const result of results) {
|
||||
const status = result.skipped ? 'SKIP' : (result.passed ? 'PASS' : 'FAIL');
|
||||
console.log(` [${status}] ${result.name}`);
|
||||
}
|
||||
|
||||
const passedCount = results.filter(r => r.passed && !r.skipped).length;
|
||||
const skippedCount = results.filter(r => r.skipped).length;
|
||||
const totalTests = results.length - skippedCount;
|
||||
|
||||
console.log('\n' + '='.repeat(60));
|
||||
console.log(`[${family.toUpperCase()}] ${allPassed ? 'ALL TESTS PASSED' : 'SOME TESTS FAILED'} (${passedCount}/${totalTests})`);
|
||||
console.log('='.repeat(60));
|
||||
|
||||
return allPassed;
|
||||
}
|
||||
|
||||
async function runTests() {
|
||||
console.log('');
|
||||
console.log('='.repeat(60));
|
||||
console.log('CACHE CONTROL FIELD STRIPPING TEST (Issue #189)');
|
||||
console.log('='.repeat(60));
|
||||
console.log('');
|
||||
console.log('This test verifies that cache_control fields are properly');
|
||||
console.log('stripped from all content blocks before sending to Cloud Code API.');
|
||||
console.log('');
|
||||
|
||||
const models = await getTestModels();
|
||||
let allPassed = true;
|
||||
|
||||
for (const { family, model } of models) {
|
||||
console.log('\n');
|
||||
const passed = await runTestsForModel(family, model);
|
||||
if (!passed) allPassed = false;
|
||||
}
|
||||
|
||||
console.log('\n' + '='.repeat(60));
|
||||
console.log('FINAL RESULT');
|
||||
console.log('='.repeat(60));
|
||||
console.log(`Overall: ${allPassed ? 'ALL MODEL FAMILIES PASSED' : 'SOME MODEL FAMILIES FAILED'}`);
|
||||
console.log('='.repeat(60));
|
||||
|
||||
process.exit(allPassed ? 0 : 1);
|
||||
}
|
||||
|
||||
runTests().catch(err => {
|
||||
console.error('Test failed with error:', err);
|
||||
process.exit(1);
|
||||
});
|
||||
@@ -77,6 +77,12 @@ async function runTests() {
|
||||
}
|
||||
}
|
||||
|
||||
function assertNotNull(value, message = '') {
|
||||
if (value === null || value === undefined) {
|
||||
throw new Error(`${message}\nExpected non-null value but got: ${value}`);
|
||||
}
|
||||
}
|
||||
|
||||
function assertWithin(actual, min, max, message = '') {
|
||||
if (actual < min || actual > max) {
|
||||
throw new Error(`${message}\nExpected value between ${min} and ${max}, got: ${actual}`);
|
||||
@@ -691,7 +697,7 @@ async function runTests() {
|
||||
assertEqual(result.account.email, 'account3@example.com', 'Oldest account should be selected');
|
||||
});
|
||||
|
||||
test('HybridStrategy: filters out unhealthy accounts', () => {
|
||||
test('HybridStrategy: uses emergency fallback for unhealthy accounts', () => {
|
||||
const strategy = new HybridStrategy({
|
||||
healthScore: { initial: 40, minUsable: 50 },
|
||||
tokenBucket: { initialTokens: 50, maxTokens: 50 }
|
||||
@@ -699,19 +705,25 @@ async function runTests() {
|
||||
const accounts = createMockAccounts(3);
|
||||
|
||||
// All accounts start with health 40, which is below minUsable 50
|
||||
// But emergency fallback should still return an account
|
||||
const result = strategy.selectAccount(accounts, 'model');
|
||||
assertNull(result.account, 'Should filter all accounts with low health');
|
||||
assertNotNull(result.account, 'Emergency fallback should return an account');
|
||||
// waitMs indicates fallback was used (250ms for emergency)
|
||||
assertTrue(result.waitMs >= 250, 'Emergency fallback should add throttle delay');
|
||||
});
|
||||
|
||||
test('HybridStrategy: filters out accounts without tokens', () => {
|
||||
test('HybridStrategy: uses last resort fallback for accounts without tokens', () => {
|
||||
const strategy = new HybridStrategy({
|
||||
healthScore: { initial: 70 },
|
||||
tokenBucket: { initialTokens: 0, maxTokens: 50 }
|
||||
});
|
||||
const accounts = createMockAccounts(3);
|
||||
|
||||
// No tokens, but last resort fallback should still return an account
|
||||
const result = strategy.selectAccount(accounts, 'model');
|
||||
assertNull(result.account, 'Should filter all accounts without tokens');
|
||||
assertNotNull(result.account, 'Last resort fallback should return an account');
|
||||
// waitMs indicates fallback was used (500ms for lastResort)
|
||||
assertTrue(result.waitMs >= 500, 'Last resort fallback should add throttle delay');
|
||||
});
|
||||
|
||||
test('HybridStrategy: consumes token on selection', () => {
|
||||
@@ -993,7 +1005,7 @@ async function runTests() {
|
||||
assertEqual(result.account.email, 'account2@example.com');
|
||||
});
|
||||
|
||||
test('Integration: Token consumption limits requests', () => {
|
||||
test('Integration: Token exhaustion triggers last resort fallback', () => {
|
||||
const strategy = new HybridStrategy({
|
||||
tokenBucket: { initialTokens: 2, maxTokens: 10 }
|
||||
});
|
||||
@@ -1003,9 +1015,11 @@ async function runTests() {
|
||||
strategy.selectAccount(accounts, 'model'); // 2 -> 1
|
||||
strategy.selectAccount(accounts, 'model'); // 1 -> 0
|
||||
|
||||
// Third request should fail (no tokens)
|
||||
// Third request should use last resort fallback (not null)
|
||||
const result = strategy.selectAccount(accounts, 'model');
|
||||
assertNull(result.account, 'Should return null when tokens exhausted');
|
||||
assertNotNull(result.account, 'Last resort fallback should return an account');
|
||||
// waitMs indicates fallback was used (500ms for lastResort)
|
||||
assertTrue(result.waitMs >= 500, 'Last resort fallback should add throttle delay');
|
||||
});
|
||||
|
||||
test('Integration: Multi-model rate limiting is independent', () => {
|
||||
|
||||
Reference in New Issue
Block a user