airkjw/CLIProxyAPI
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge pull request #2389 from router-for-me/claude

Browse Source 
fix(claude): add default max_tokens for models
This commit is contained in:
Luis Pater
2026-03-29 13:03:20 +08:00
committed by GitHub
parent 9b7d7021af f033d3a6df
commit 1587ff5e74
2 changed files with 108 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

30
internal/runtime/executor/claude_executor.go
View File

@@ -22,6 +22,7 @@ import (
claudeauth "github.com/router-for-me/CLIProxyAPI/v6/internal/auth/claude"
"github.com/router-for-me/CLIProxyAPI/v6/internal/config"
"github.com/router-for-me/CLIProxyAPI/v6/internal/misc"
"github.com/router-for-me/CLIProxyAPI/v6/internal/registry"
"github.com/router-for-me/CLIProxyAPI/v6/internal/thinking"
"github.com/router-for-me/CLIProxyAPI/v6/internal/util"
cliproxyauth "github.com/router-for-me/CLIProxyAPI/v6/sdk/cliproxy/auth"
@@ -44,6 +45,10 @@ type ClaudeExecutor struct {
// Previously "proxy_" was used but this is a detectable fingerprint difference.
const claudeToolPrefix = ""
// Anthropic-compatible upstreams may reject or even crash when Claude models
// omit max_tokens. Prefer registered model metadata before using a fallback.
const defaultModelMaxTokens = 1024
func NewClaudeExecutor(cfg *config.Config) *ClaudeExecutor { return &ClaudeExecutor{cfg: cfg} }
func (e *ClaudeExecutor) Identifier() string { return "claude" }
@@ -127,6 +132,7 @@ func (e *ClaudeExecutor) Execute(ctx context.Context, auth *cliproxyauth.Auth, r
requestedModel := payloadRequestedModel(opts, req.Model)
body = applyPayloadConfigWithRoot(e.cfg, baseModel, to.String(), "", body, originalTranslated, requestedModel)
body = ensureModelMaxTokens(body, baseModel)
// Disable thinking if tool_choice forces tool use (Anthropic API constraint)
body = disableThinkingIfToolChoiceForced(body)
@@ -293,6 +299,7 @@ func (e *ClaudeExecutor) ExecuteStream(ctx context.Context, auth *cliproxyauth.A
requestedModel := payloadRequestedModel(opts, req.Model)
body = applyPayloadConfigWithRoot(e.cfg, baseModel, to.String(), "", body, originalTranslated, requestedModel)
body = ensureModelMaxTokens(body, baseModel)
// Disable thinking if tool_choice forces tool use (Anthropic API constraint)
body = disableThinkingIfToolChoiceForced(body)
@@ -1880,3 +1887,26 @@ func injectSystemCacheControl(payload []byte) []byte {
return payload
}
func ensureModelMaxTokens(body []byte, modelID string) []byte {
if len(body) == 0 || !gjson.ValidBytes(body) {
return body
}
if maxTokens := gjson.GetBytes(body, "max_tokens"); maxTokens.Exists() {
return body
}
for _, provider := range registry.GetGlobalRegistry().GetModelProviders(strings.TrimSpace(modelID)) {
if strings.EqualFold(provider, "claude") {
maxTokens := defaultModelMaxTokens
if info := registry.GetGlobalRegistry().GetModelInfo(strings.TrimSpace(modelID), "claude"); info != nil && info.MaxCompletionTokens > 0 {
maxTokens = info.MaxCompletionTokens
}
body, _ = sjson.SetBytes(body, "max_tokens", maxTokens)
return body
}
}
return body
}

78
internal/runtime/executor/claude_executor_test.go
View File

@@ -15,6 +15,7 @@ import (
"github.com/gin-gonic/gin"
"github.com/klauspost/compress/zstd"
"github.com/router-for-me/CLIProxyAPI/v6/internal/config"
"github.com/router-for-me/CLIProxyAPI/v6/internal/registry"
cliproxyauth "github.com/router-for-me/CLIProxyAPI/v6/sdk/cliproxy/auth"
cliproxyexecutor "github.com/router-for-me/CLIProxyAPI/v6/sdk/cliproxy/executor"
sdktranslator "github.com/router-for-me/CLIProxyAPI/v6/sdk/translator"
@@ -1183,6 +1184,83 @@ func testClaudeExecutorInvalidCompressedErrorBody(
}
}
func TestEnsureModelMaxTokens_UsesRegisteredMaxCompletionTokens(t *testing.T) {
reg := registry.GetGlobalRegistry()
clientID := "test-claude-max-completion-tokens-client"
modelID := "test-claude-max-completion-tokens-model"
reg.RegisterClient(clientID, "claude", []*registry.ModelInfo{{
ID: modelID,
Type: "claude",
OwnedBy: "anthropic",
Object: "model",
Created: time.Now().Unix(),
MaxCompletionTokens: 4096,
UserDefined: true,
}})
defer reg.UnregisterClient(clientID)
input := []byte(`{"model":"test-claude-max-completion-tokens-model","messages":[{"role":"user","content":"hi"}]}`)
out := ensureModelMaxTokens(input, modelID)
if got := gjson.GetBytes(out, "max_tokens").Int(); got != 4096 {
t.Fatalf("max_tokens = %d, want %d", got, 4096)
}
}
func TestEnsureModelMaxTokens_DefaultsMissingValue(t *testing.T) {
reg := registry.GetGlobalRegistry()
clientID := "test-claude-default-max-tokens-client"
modelID := "test-claude-default-max-tokens-model"
reg.RegisterClient(clientID, "claude", []*registry.ModelInfo{{
ID: modelID,
Type: "claude",
OwnedBy: "anthropic",
Object: "model",
Created: time.Now().Unix(),
UserDefined: true,
}})
defer reg.UnregisterClient(clientID)
input := []byte(`{"model":"test-claude-default-max-tokens-model","messages":[{"role":"user","content":"hi"}]}`)
out := ensureModelMaxTokens(input, modelID)
if got := gjson.GetBytes(out, "max_tokens").Int(); got != defaultModelMaxTokens {
t.Fatalf("max_tokens = %d, want %d", got, defaultModelMaxTokens)
}
}
func TestEnsureModelMaxTokens_PreservesExplicitValue(t *testing.T) {
reg := registry.GetGlobalRegistry()
clientID := "test-claude-preserve-max-tokens-client"
modelID := "test-claude-preserve-max-tokens-model"
reg.RegisterClient(clientID, "claude", []*registry.ModelInfo{{
ID: modelID,
Type: "claude",
OwnedBy: "anthropic",
Object: "model",
Created: time.Now().Unix(),
MaxCompletionTokens: 4096,
UserDefined: true,
}})
defer reg.UnregisterClient(clientID)
input := []byte(`{"model":"test-claude-preserve-max-tokens-model","max_tokens":2048,"messages":[{"role":"user","content":"hi"}]}`)
out := ensureModelMaxTokens(input, modelID)
if got := gjson.GetBytes(out, "max_tokens").Int(); got != 2048 {
t.Fatalf("max_tokens = %d, want %d", got, 2048)
}
}
func TestEnsureModelMaxTokens_SkipsUnregisteredModel(t *testing.T) {
input := []byte(`{"model":"test-claude-unregistered-model","messages":[{"role":"user","content":"hi"}]}`)
out := ensureModelMaxTokens(input, "test-claude-unregistered-model")
if gjson.GetBytes(out, "max_tokens").Exists() {
t.Fatalf("max_tokens should remain unset, got %s", gjson.GetBytes(out, "max_tokens").Raw)
}
}
// TestClaudeExecutor_ExecuteStream_SetsIdentityAcceptEncoding verifies that streaming
// requests use Accept-Encoding: identity so the upstream cannot respond with a
// compressed SSE body that would silently break the line scanner.