fix: report cache reads in streaming and correct cost calculation (#577)

* fix: report cache reads in streaming and correct cost calculation

Fix two bugs in how the OpenAI-to-Anthropic shim handles cached tokens:

1. codexShim: streaming message_delta missing cache_read_input_tokens
   The codexStreamToAnthropic() function builds the final message_delta
   usage object inline (not through makeUsage()), and only included
   input_tokens and output_tokens. cache_read_input_tokens was always 0,
   so /cost never showed cache reads for Responses API models (GPT-5+).

   Also fix makeUsage() to read input_tokens_details.cached_tokens and
   prompt_tokens_details.cached_tokens for the non-streaming path.

2. Both shims: cost double-counting from convention mismatch
   OpenAI includes cached tokens in input_tokens/prompt_tokens (i.e.,
   input_tokens = uncached + cached). Anthropic treats input_tokens as
   uncached only. The cost formula was:
     cost = input_tokens * inputRate + cache_read * cacheRate
   This double-counts cached tokens. Fix by subtracting cached from
   input during the conversion:
     input_tokens = prompt_tokens - cached_tokens

   In practice this was inflating reported costs by ~2x for sessions
   with high cache hit rates (which is most sessions, since Copilot
   auto-caches server-side).

Fixes #515

* fix: omit zero cache read/write fields from /cost output

Only show "cache read" and "cache write" in /cost per-model usage when
the value is > 0. Providers like GitHub Copilot never report
cache_creation_input_tokens (the server manages its own cache), so
showing "0 cache write" on every line is misleading — it implies caching
is not working when it actually is.

Before:
  claude-haiku:  2.6k input, 151 output, 39.8k cache read, 0 cache write ($0.04)

After:
  claude-haiku:  2.6k input, 151 output, 39.8k cache read ($0.04)

---------

Co-authored-by: Zartris <14197299+Zartris@users.noreply.github.com>

src/cost-tracker.ts

@@ -181,7 +181,7 @@ function formatCost(cost: number, maxDecimalPlaces: number = 4): string {
 function formatModelUsage(): string {
   const modelUsageMap = getModelUsage()
   if (Object.keys(modelUsageMap).length === 0) {
-    return 'Usage:                 0 input, 0 output, 0 cache read, 0 cache write'
+    return 'Usage:                 0 input, 0 output'
   }
 
   // Accumulate usage by short name
@@ -211,15 +211,19 @@ function formatModelUsage(): string {
 
   let result = 'Usage by model:'
   for (const [shortName, usage] of Object.entries(usageByShortName)) {
-    const usageString =
+    let usageString =
       `  ${formatNumber(usage.inputTokens)} input, ` +
-      `${formatNumber(usage.outputTokens)} output, ` +
-      `${formatNumber(usage.cacheReadInputTokens)} cache read, ` +
-      `${formatNumber(usage.cacheCreationInputTokens)} cache write` +
-      (usage.webSearchRequests > 0
-        ? `, ${formatNumber(usage.webSearchRequests)} web search`
-        : '') +
-      ` (${formatCost(usage.costUSD)})`
+      `${formatNumber(usage.outputTokens)} output`
+    if (usage.cacheReadInputTokens > 0) {
+      usageString += `, ${formatNumber(usage.cacheReadInputTokens)} cache read`
+    }
+    if (usage.cacheCreationInputTokens > 0) {
+      usageString += `, ${formatNumber(usage.cacheCreationInputTokens)} cache write`
+    }
+    if (usage.webSearchRequests > 0) {
+      usageString += `, ${formatNumber(usage.webSearchRequests)} web search`
+    }
+    usageString += ` (${formatCost(usage.costUSD)})`
     result += `\n` + `${shortName}:`.padStart(21) + usageString
   }
   return result