fix: use relative API paths instead of hardcoded localhost

frontend/src/components/ContextManager.vue

@@ -169,7 +169,7 @@ const parsedNodes = computed(() => {
 
 const fetchNodes = async () => {
   try {
-    const res = await axios.get('http://127.0.0.1:8000/context_nodes/')
+    const res = await axios.get('/context_nodes/')
     nodes.value = res.data
   } catch (error) {
     message.error('获取认知节点失败')
@@ -178,7 +178,7 @@ const fetchNodes = async () => {
 
 const createNode = async () => {
   try {
-    const res = await axios.post('http://127.0.0.1:8000/context_nodes/', formValue.value)
+    const res = await axios.post('/context_nodes/', formValue.value)
     message.success('认知已提交！')
     nodes.value.push(res.data)
     showModal.value = false

frontend/src/components/ExperimentBoard.vue

@@ -97,7 +97,7 @@ const getStatusLabel = (status: string) => {
 
 const fetchExperiments = async () => {
   try {
-    const res = await axios.get('http://127.0.0.1:8000/experiments/')
+    const res = await axios.get('/experiments/')
     experiments.value = res.data
   } catch (error) {
     message.error('获取实验列表失败')
@@ -106,7 +106,7 @@ const fetchExperiments = async () => {
 
 const fetchContextNodes = async () => {
   try {
-    const res = await axios.get('http://127.0.0.1:8000/context_nodes/')
+    const res = await axios.get('/context_nodes/')
     contextNodes.value = res.data
   } catch (error) {
     console.error('Failed to fetch context nodes')
@@ -120,7 +120,7 @@ const openModal = () => {
 
 const createExperiment = async () => {
   try {
-    const res = await axios.post('http://127.0.0.1:8000/experiments/', formValue.value)
+    const res = await axios.post('/experiments/', formValue.value)
     message.success('实验已启动！')
     experiments.value.push(res.data)
     showModal.value = false

frontend/src/components/LLMSettings.vue

@@ -232,7 +232,7 @@ const selectProvider = (value: string) => {
 const testConnection = async () => {
   testing.value = true
   try {
-    const response = await axios.get(`${config.ollama_host.replace(':11434', ':8000')}/ai/status`, { timeout: 5000 })
+    const response = await axios.get(`/ai/status`, { timeout: 5000 })
     if (response.data.status === 'ready') {
       isConnected.value = true
       statusText.value = `${response.data.model_count} 个模型`
@@ -251,7 +251,7 @@ const testConnection = async () => {
 
 const loadConfig = async () => {
   try {
-    const response = await axios.get('http://127.0.0.1:8000/ai/config')
+    const response = await axios.get('/ai/config')
     config.provider = response.data.provider
     config.ollama_host = response.data.ollama_host
   } catch {}
@@ -260,7 +260,7 @@ const loadConfig = async () => {
 const saveConfig = async () => {
   saving.value = true
   try {
-    await axios.post('http://127.0.0.1:8000/ai/config', {
+    await axios.post('/ai/config', {
       provider: config.provider,
       deepseek_api_key: config.deepseek_api_key || undefined,
       openai_api_key: config.openai_api_key || undefined,
@@ -284,7 +284,7 @@ const resetConfig = () => {
 
 const restartBackend = async () => {
   try {
-    await axios.post('http://127.0.0.1:8000/ai/stop')
+    await axios.post('/ai/stop')
     saveStatus.value = '后端已停止，请手动启动'
     showRestartModal.value = false
   } catch {

frontend/src/components/SignalDashboard.vue

@@ -1186,7 +1186,7 @@ const submitFeedback = async (agreed: boolean) => {
     const aiPrediction = currentStrategicInfo.value.is_strategic
     const userFeedback = agreed ? aiPrediction : !aiPrediction
 
-    const response = await axios.post(`http://127.0.0.1:8000/signals/${selectedSignal.value.id}/feedback`, {
+    const response = await axios.post(`/signals/${selectedSignal.value.id}/feedback`, {
       signal_id: selectedSignal.value.id,
       was_strategic: userFeedback,
       reason: agreed ? 'AI判断准确' : 'AI判断不准确'
@@ -1447,7 +1447,7 @@ watch(selectedSignal, (newVal, oldVal) => {
 // Load existing feedback for a signal
 const loadSignalFeedback = async (signalId: string) => {
   try {
-    const response = await axios.get(`http://127.0.0.1:8000/signals/${signalId}/feedbacks`)
+    const response = await axios.get(`/signals/${signalId}/feedbacks`)
     if (response.data && response.data.length > 0) {
       const latestFeedback = response.data[0]
       signalFeedback.value = latestFeedback
@@ -1505,7 +1505,7 @@ const isNewSignal = (signal: any) => {
 const fetchSignals = async (isPoll = false) => {
   if (!isPoll) loading.value = true
   try {
-    const res = await axios.get('http://127.0.0.1:8000/signals/')
+    const res = await axios.get('/signals/')
     const newSignals = res.data
     
     // Check for task status updates if polling
@@ -1579,7 +1579,7 @@ const submitSignal = async () => {
   if (!formValue.value.content) return
   submitting.value = true
   try {
-    const res = await axios.post('http://127.0.0.1:8000/signals/ingest', formValue.value)
+    const res = await axios.post('/signals/ingest', formValue.value)
     message.success('信号已注入，战略评估完成！')
     showModal.value = false
     await fetchSignals()
@@ -1590,7 +1590,7 @@ const submitSignal = async () => {
     }
 
     // 停止 Ollama 节省资源
-    await axios.post('http://127.0.0.1:8000/ai/stop')
+    await axios.post('/ai/stop')
     ollamaReady.value = false
     message.info('🌱 Ollama 已停止，节省资源')
   } catch (error) {
@@ -1603,7 +1603,7 @@ const submitSignal = async () => {
 // 检查 AI 服务状态
 const checkOllamaStatus = async () => {
   try {
-    const response = await axios.get('http://127.0.0.1:8000/ai/status', { timeout: 3000 })
+    const response = await axios.get('/ai/status', { timeout: 3000 })
 
     const data = response.data
     providerType.value = data.provider_type || 'cloud'
@@ -1634,7 +1634,7 @@ const checkOllamaStatus = async () => {
 const startOllama = async () => {
   startingOllama.value = true
   try {
-    const response = await axios.post('http://127.0.0.1:8000/ai/start')
+    const response = await axios.post('/ai/start')
 
     if (response.data.status === 'already_running') {
       message.info('Ollama 已在运行')
@@ -1660,7 +1660,7 @@ const startOllama = async () => {
 // 停止本地 Ollama
 const stopOllama = async () => {
   try {
-    await axios.post('http://127.0.0.1:8000/ai/stop')
+    await axios.post('/ai/stop')
     ollamaReady.value = false
     message.success('✅ Ollama 已停止，内存已释放')
   } catch (error) {
@@ -1691,7 +1691,7 @@ const startAnalysis = async () => {
 
     // 调用后端获取并分析信号
     analysisStatus.value = '正在获取 HackerNews 信号...'
-    const response = await axios.post('http://127.0.0.1:8000/signals/fetch')
+    const response = await axios.post('/signals/fetch')
 
     clearInterval(progressInterval)
     analysisProgress.value = 100
@@ -1708,7 +1708,7 @@ const startAnalysis = async () => {
     // 仅本地 Ollama 需要停止节省资源
     if (providerType.value === 'local') {
       analysisStatus.value = '正在停止 Ollama...'
-      await axios.post('http://127.0.0.1:8000/ai/stop')
+      await axios.post('/ai/stop')
       ollamaReady.value = false
       analysisStatus.value = `完成！Ollama 已停止`
     } else {