mirror of
https://github.com/tiennm99/goclaw.git
synced 2026-10-04 10:13:16 +00:00
Plateau Nguyen
0e994f959c
* feat(providers): explicit prompt cache for DashScope/Qwen Extend OpenAI-compat path with Anthropic-style cache_control:ephemeral inline blocks for Alibaba DashScope endpoints (provider_type=bailian or URL contains "dashscope"). Verified live: qwen3.6-plus / qwen3.5-plus / qwen3-coder-plus all return 99.7% cache hit rate on 6K-token prefix, yielding ~89% token cost reduction on cached prefix (90% Alibaba discount). - isDashScope(): 3-source detection (URL + providerType + name) handles reverse-proxied endpoints; covers both "dashscope" and "bailian" - buildRequestBody wraps system content with SplitSystemPromptForCache (exported from anthropic_request.go) using <!-- GOCLAW_CACHE_BOUNDARY --> - Tool prefix cache: cache_control on last tool definition, with 4-marker budget guard - Parse cache_creation_input_tokens from prompt_tokens_details into Usage.CacheCreationTokens; propagates via existing span metadata writers - Runtime escape hatch: GOCLAW_DISABLE_DASHSCOPE_CACHE=true - Live integration smoke test (build tag integration, env-gated) * chore(providers): polish per PR #1127 review - Use strings.Repeat instead of custom repeat() helper in smoke test - Clarify BuildRequestBodyForTest is test-only, not public API * feat(providers): enable thinking for Qwen 3.7/3.6, observe cache in smoke test Qwen3.7-plus and qwen3.6-plus support deep thinking but were missing from dashscopeThinkingModels, so enable_thinking/thinking_budget was silently skipped. Add both to the whitelist and test. Add qwen3.7-plus to the cache smoke test as cache-optional: Alibaba's context-cache doc does not yet list 3.7/3.6 for explicit cache, and the cache wrap is a safe no-op when unsupported, so a no-cache result is logged rather than failed to avoid a flaky live assertion. Claude-Session: https://claude.ai/code/session_01X3jkrc7N3ar8ZGzUJWyNS5 * fix(providers): preserve DashScope detection for proxy routes
74 lines
2.5 KiB
Go
74 lines
2.5 KiB
Go
package providers
|
|
|
|
import (
|
|
"testing"
|
|
)
|
|
|
|
// TestAnthropicSystemBlocksSplit verifies that a system prompt with
|
|
// the cache boundary marker is split into 2 blocks: stable (cached) + dynamic.
|
|
func TestAnthropicSystemBlocksSplit(t *testing.T) {
|
|
prompt := "stable content\n" + CacheBoundaryMarker + "\ndynamic content"
|
|
blocks := SplitSystemPromptForCache(prompt)
|
|
if len(blocks) != 2 {
|
|
t.Fatalf("expected 2 blocks, got %d", len(blocks))
|
|
}
|
|
if blocks[0]["text"] != "stable content" {
|
|
t.Errorf("block[0] text = %q, want %q", blocks[0]["text"], "stable content")
|
|
}
|
|
if blocks[0]["cache_control"] == nil {
|
|
t.Error("block[0] missing cache_control")
|
|
}
|
|
if blocks[1]["text"] != "dynamic content" {
|
|
t.Errorf("block[1] text = %q, want %q", blocks[1]["text"], "dynamic content")
|
|
}
|
|
if blocks[1]["cache_control"] != nil {
|
|
t.Error("block[1] should NOT have cache_control")
|
|
}
|
|
}
|
|
|
|
// TestAnthropicSingleBlockFallback verifies backward compat: no boundary
|
|
// marker → single block with cache_control.
|
|
func TestAnthropicSingleBlockFallback(t *testing.T) {
|
|
prompt := "no boundary here"
|
|
blocks := SplitSystemPromptForCache(prompt)
|
|
if len(blocks) != 1 {
|
|
t.Fatalf("expected 1 block, got %d", len(blocks))
|
|
}
|
|
if blocks[0]["text"] != "no boundary here" {
|
|
t.Errorf("block text = %q", blocks[0]["text"])
|
|
}
|
|
if blocks[0]["cache_control"] == nil {
|
|
t.Error("single block missing cache_control")
|
|
}
|
|
}
|
|
|
|
// TestAnthropicEmptyDynamic verifies that an empty dynamic section
|
|
// after the boundary produces only 1 block (no empty block appended).
|
|
func TestAnthropicEmptyDynamic(t *testing.T) {
|
|
prompt := "stable only\n" + CacheBoundaryMarker + "\n"
|
|
blocks := SplitSystemPromptForCache(prompt)
|
|
if len(blocks) != 1 {
|
|
t.Fatalf("expected 1 block for empty dynamic, got %d", len(blocks))
|
|
}
|
|
if blocks[0]["text"] != "stable only" {
|
|
t.Errorf("block text = %q", blocks[0]["text"])
|
|
}
|
|
}
|
|
|
|
// TestAnthropicEmptyStable verifies that a boundary at the very start
|
|
// (empty stable section) still produces valid blocks without empty text.
|
|
func TestAnthropicEmptyStable(t *testing.T) {
|
|
prompt := CacheBoundaryMarker + "\ndynamic only"
|
|
blocks := SplitSystemPromptForCache(prompt)
|
|
// Stable is empty string after TrimSpace — should still produce a block
|
|
// (Anthropic API handles empty text blocks gracefully).
|
|
if len(blocks) < 1 {
|
|
t.Fatal("expected at least 1 block")
|
|
}
|
|
// The dynamic block should have the actual content.
|
|
last := blocks[len(blocks)-1]
|
|
if last["text"] != "dynamic only" {
|
|
t.Errorf("dynamic block text = %q, want %q", last["text"], "dynamic only")
|
|
}
|
|
}
|