feat: show normalized prompt cache hit rates

Token usage previously showed cache reads and writes without a comparable hit rate. Activity usage now calculates a weighted cache hit rate using OpenAI-compatible input totals and Anthropic's separately reported input, cache-read, and cache-write tokens, then shows it in totals and grouped details.

Release note: Token 用量统计新增缓存命中率，并针对 OpenAI 兼容接口与 Anthropic Messages 的不同上报口径进行归一化计算。

src/main/assistant/assistant-database.test.ts

@@ -2175,6 +2175,7 @@ describe('AssistantDatabase', () => {
         output: 25,
         cacheRead: 40,
         cacheWrite: 12,
+        cacheInput: 177,
         totalTokens: 150
       },
       records: [
@@ -2185,6 +2186,7 @@ describe('AssistantDatabase', () => {
           output: 25,
           cacheRead: 40,
           cacheWrite: 12,
+          cacheInput: 177,
           totalTokens: 150
         })
       ]
@@ -2334,6 +2336,7 @@ describe('AssistantDatabase', () => {
       output: 105,
       cacheRead: 42,
       cacheWrite: 15,
+      cacheInput: 312,
       totalTokens: 360
     })
     expect(summary.records).toHaveLength(3)
@@ -2353,6 +2356,7 @@ describe('AssistantDatabase', () => {
           output: 60,
           cacheRead: 35,
           cacheWrite: 12,
+          cacheInput: 197,
           totalTokens: 210
         }),
         expect.objectContaining({
@@ -2684,6 +2688,7 @@ describe('AssistantDatabase', () => {
         output: 0,
         cacheRead: 0,
         cacheWrite: 0,
+        cacheInput: 0,
         totalTokens: 0
       },
       records: []

src/main/assistant/assistant-database.ts

@@ -317,6 +317,7 @@ type TokenUsageRecordRow = {
   output_tokens: number
   cache_read_tokens: number
   cache_write_tokens: number
+  cache_input_tokens: number
 }
 
 type ComputerControlActionRow = {
@@ -2799,7 +2800,15 @@ export class AssistantDatabase {
            SUM(usage.input_tokens) AS input_tokens,
            SUM(usage.output_tokens) AS output_tokens,
            SUM(usage.cache_read_tokens) AS cache_read_tokens,
-           SUM(usage.cache_write_tokens) AS cache_write_tokens
+           SUM(usage.cache_write_tokens) AS cache_write_tokens,
+           SUM(
+             usage.input_tokens +
+             CASE
+               WHEN LOWER(usage.provider) LIKE '%anthropic%'
+               THEN usage.cache_read_tokens + usage.cache_write_tokens
+               ELSE 0
+             END
+           ) AS cache_input_tokens
          FROM model_usage_calls usage
          JOIN tasks ON tasks.id = usage.request_id
          LEFT JOIN projects ON projects.id = tasks.project_id
@@ -2832,6 +2841,7 @@ export class AssistantDatabase {
       output: row.output_tokens,
       cacheRead: row.cache_read_tokens,
       cacheWrite: row.cache_write_tokens,
+      cacheInput: row.cache_input_tokens,
       totalTokens: row.input_tokens + row.output_tokens
     }))
     const totalRow = this.requireDatabase()
@@ -2841,7 +2851,18 @@ export class AssistantDatabase {
            COALESCE(SUM(input_tokens), 0) AS input_tokens,
            COALESCE(SUM(output_tokens), 0) AS output_tokens,
            COALESCE(SUM(cache_read_tokens), 0) AS cache_read_tokens,
-           COALESCE(SUM(cache_write_tokens), 0) AS cache_write_tokens
+           COALESCE(SUM(cache_write_tokens), 0) AS cache_write_tokens,
+           COALESCE(
+             SUM(
+               input_tokens +
+               CASE
+                 WHEN LOWER(provider) LIKE '%anthropic%'
+                 THEN cache_read_tokens + cache_write_tokens
+                 ELSE 0
+               END
+             ),
+             0
+           ) AS cache_input_tokens
          FROM model_usage_calls`
       )
       .get() as {
@@ -2850,6 +2871,7 @@ export class AssistantDatabase {
       output_tokens: number
       cache_read_tokens: number
       cache_write_tokens: number
+      cache_input_tokens: number
     }
     const totals = {
       callCount: totalRow.call_count,
@@ -2857,6 +2879,7 @@ export class AssistantDatabase {
       output: totalRow.output_tokens,
       cacheRead: totalRow.cache_read_tokens,
       cacheWrite: totalRow.cache_write_tokens,
+      cacheInput: totalRow.cache_input_tokens,
       totalTokens: totalRow.input_tokens + totalRow.output_tokens
     }
     return { totals, records }