From 7fe4deff0d90de4591e0b4ec15f96bc4b020c85d Mon Sep 17 00:00:00 2001
From: A Magno <ale@magno.me>
Date: Mon, 2 Mar 2026 14:16:13 +0100
Subject: [PATCH] perf: align with readme-magno optimizations (timestamp, cache
 logging)

- Change system prompt timestamp to daily-only format (was HH:MM,
  invalidating dynamic block every minute unnecessarily)
- Add CacheCreatedTokens and CacheReadTokens to UsageInfo
- Extract Anthropic cache_creation/cache_read tokens in parseResponse
- Log cache hit/miss stats per session for cost monitoring

Made-with: Cursor
---
 pkg/agent/context.go                 |  2 +-
 pkg/agent/loop.go                    | 16 ++++++++++------
 pkg/providers/anthropic/provider.go  |  8 +++++---
 pkg/providers/protocoltypes/types.go |  8 +++++---
 4 files changed, 21 insertions(+), 13 deletions(-)

diff --git a/pkg/agent/context.go b/pkg/agent/context.go
index ab9c36d05..583377272 100644
--- a/pkg/agent/context.go
+++ b/pkg/agent/context.go
@@ -367,7 +367,7 @@ func (cb *ContextBuilder) LoadBootstrapFiles() string {
 // See: https://docs.anthropic.com/en/docs/build-with-claude/prompt-caching
 // See: https://platform.openai.com/docs/guides/prompt-caching
 func (cb *ContextBuilder) buildDynamicContext(channel, chatID string) string {
-	now := time.Now().Format("2006-01-02 15:04 (Monday)")
+	now := time.Now().Format("2006-01-02 (Monday)")
 	rt := fmt.Sprintf("%s %s, Go %s", runtime.GOOS, runtime.GOARCH, runtime.Version())
 
 	var sb strings.Builder
diff --git a/pkg/agent/loop.go b/pkg/agent/loop.go
index 973a1a45a..0b405586c 100644
--- a/pkg/agent/loop.go
+++ b/pkg/agent/loop.go
@@ -661,7 +661,7 @@ func (al *AgentLoop) runLLMIteration(
 ) (string, int, error) {
 	iteration := 0
 	var finalContent string
-	var totalInputTokens, totalOutputTokens int
+	var totalInputTokens, totalOutputTokens, totalCacheCreated, totalCacheRead int
 
 	for iteration < agent.MaxIterations {
 		iteration++
@@ -809,6 +809,8 @@ func (al *AgentLoop) runLLMIteration(
 		if response.Usage != nil {
 			totalInputTokens += response.Usage.PromptTokens
 			totalOutputTokens += response.Usage.CompletionTokens
+			totalCacheCreated += response.Usage.CacheCreatedTokens
+			totalCacheRead += response.Usage.CacheReadTokens
 		}
 
 		logger.DebugCF("agent", "LLM response",
@@ -988,11 +990,13 @@ func (al *AgentLoop) runLLMIteration(
 	if totalInputTokens > 0 || totalOutputTokens > 0 {
 		logger.InfoCF("agent", "Session token usage",
 			map[string]any{
-				"agent_id":      agent.ID,
-				"iterations":    iteration,
-				"input_tokens":  totalInputTokens,
-				"output_tokens": totalOutputTokens,
-				"total_tokens":  totalInputTokens + totalOutputTokens,
+				"agent_id":       agent.ID,
+				"iterations":     iteration,
+				"input_tokens":   totalInputTokens,
+				"output_tokens":  totalOutputTokens,
+				"total_tokens":   totalInputTokens + totalOutputTokens,
+				"cache_created":  totalCacheCreated,
+				"cache_read":     totalCacheRead,
 			})
 	}
 
diff --git a/pkg/providers/anthropic/provider.go b/pkg/providers/anthropic/provider.go
index 1f77f16b8..1c8dfc563 100644
--- a/pkg/providers/anthropic/provider.go
+++ b/pkg/providers/anthropic/provider.go
@@ -303,9 +303,11 @@ func parseResponse(resp *anthropic.Message) *LLMResponse {
 		ToolCalls:    toolCalls,
 		FinishReason: finishReason,
 		Usage: &UsageInfo{
-			PromptTokens:     int(resp.Usage.InputTokens),
-			CompletionTokens: int(resp.Usage.OutputTokens),
-			TotalTokens:      int(resp.Usage.InputTokens + resp.Usage.OutputTokens),
+			PromptTokens:       int(resp.Usage.InputTokens),
+			CompletionTokens:   int(resp.Usage.OutputTokens),
+			TotalTokens:        int(resp.Usage.InputTokens + resp.Usage.OutputTokens),
+			CacheCreatedTokens: int(resp.Usage.CacheCreationInputTokens),
+			CacheReadTokens:    int(resp.Usage.CacheReadInputTokens),
 		},
 	}
 }
diff --git a/pkg/providers/protocoltypes/types.go b/pkg/providers/protocoltypes/types.go
index 99f13334e..e3ce5edd5 100644
--- a/pkg/providers/protocoltypes/types.go
+++ b/pkg/providers/protocoltypes/types.go
@@ -42,9 +42,11 @@ type ReasoningDetail struct {
 }
 
 type UsageInfo struct {
-	PromptTokens     int `json:"prompt_tokens"`
-	CompletionTokens int `json:"completion_tokens"`
-	TotalTokens      int `json:"total_tokens"`
+	PromptTokens       int `json:"prompt_tokens"`
+	CompletionTokens   int `json:"completion_tokens"`
+	TotalTokens        int `json:"total_tokens"`
+	CacheCreatedTokens int `json:"cache_created_tokens,omitempty"`
+	CacheReadTokens    int `json:"cache_read_tokens,omitempty"`
 }
 
 // CacheControl marks a content block for LLM-side prefix caching.