jianf/ModelRouter
1
0
Fork 0
mirror of https://gitcode.com/JianFeeeee/ModelRouter.git synced 2026-09-20 00:48:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: tool call anchor & wire format, streaming chunk passthrough, WebUI narrow-screen, docs bilingual

Browse Source
This commit is contained in:
root
2026-08-08 11:26:58 +08:00
parent 8e9de95274
commit 5d50b69153
18 changed files with 1119 additions and 42 deletions
Download Patch File Download Diff File Expand all files Collapse all files

81
internal/gateway/chat.go
View File

@ -44,10 +44,10 @@ type ChatChoice struct {
}
type RespMessage struct {
Role string `json:"role"`
Content string `json:"content"`
ReasoningContent string `json:"reasoning_content,omitempty"`
ToolCalls []types.ToolCall `json:"tool_calls,omitempty"`
Role string `json:"role,omitempty"`
Content string `json:"content"`
ReasoningContent string `json:"reasoning_content,omitempty"`
ToolCalls json.RawMessage `json:"tool_calls,omitempty"`
}
type ChatChunk struct {
@ -77,13 +77,49 @@ func isAuto(m string) bool {
}
// resolveCands picks the ordered candidate providers for a requested model.
func (g *Gateway) resolveCands(model string) ([]*provider.Provider, string) {
if model == "" || isAuto(model) {
// toolCalling requests are anchored: they resolve to exactly one provider
// (highest-priority available) so a tool-call round never switches models.
func (g *Gateway) resolveCands(req *chatRequest) ([]*provider.Provider, string) {
model := req.Model
if model == "" {
model = g.core.DefaultModel()
}
cands, effective := g.resolveByModel(model)
if !toolRequest(req) {
return cands, effective
}
// tool-call request: pin to one provider (no AUTO fallback across models)
if len(cands) == 0 {
return nil, effective
}
first := cands[0]
eff := first.ModelFor(model)
if eff == "" {
eff = firstModel(first)
}
return []*provider.Provider{first}, eff
}
func (g *Gateway) resolveByModel(model string) ([]*provider.Provider, string) {
if isAuto(model) {
return g.core.Registry().Resolve("AUTO"), ""
}
return g.core.Registry().Resolve(model), model
}
// toolRequest reports whether the request participates in a tool-call round.
func toolRequest(req *chatRequest) bool {
if len(req.Tools) > 0 || req.ToolChoice != nil {
return true
}
for _, m := range req.Messages {
if m.Role == "tool" || len(m.ToolCalls) > 0 {
return true
}
}
return false
}
func (g *Gateway) handleChat(w http.ResponseWriter, r *http.Request) {
if r.Method != http.MethodPost {
writeError(w, http.StatusMethodNotAllowed, "method_not_allowed", "use POST")
@ -102,7 +138,7 @@ func (g *Gateway) handleChat(w http.ResponseWriter, r *http.Request) {
if model == "" {
model = g.core.DefaultModel()
}
cands, effective := g.resolveCands(model)
cands, effective := g.resolveCands(&req)
if len(cands) == 0 {
writeError(w, http.StatusServiceUnavailable, "no_provider", "no LLM source configured")
return
@ -159,6 +195,31 @@ func imageOnly(cands []*provider.Provider) []*provider.Provider {
return out
}
// toolCallsWire converts unified tool calls to the OpenAI wire format:
// tool_calls:[{id,type,function:{name,arguments:StringJSON}}]. Clients expect
// arguments to be a JSON string, not an object.
func toolCallsWire(tcs []types.ToolCall) json.RawMessage {
wire := make([]map[string]interface{}, 0, len(tcs))
for _, tc := range tcs {
args := "{}"
if tc.Arguments != nil {
if b, err := json.Marshal(tc.Arguments); err == nil {
args = string(b)
}
}
wire = append(wire, map[string]interface{}{
"id": tc.ID,
"type": tc.Type,
"function": map[string]interface{}{
"name": tc.Name,
"arguments": args,
},
})
}
b, _ := json.Marshal(wire)
return b
}
func (g *Gateway) singleChat(w http.ResponseWriter, ctx context.Context, cands []*provider.Provider, req *types.ChatRequest, effective string) {
resp, err := g.core.Scheduler().Chat(ctx, scheduler.FromRegistry(cands), req)
if err != nil {
@ -170,7 +231,7 @@ func (g *Gateway) singleChat(w http.ResponseWriter, ctx context.Context, cands [
msg.ReasoningContent = resp.ReasoningContent
}
if len(resp.ToolCalls) > 0 {
msg.ToolCalls = resp.ToolCalls
msg.ToolCalls = toolCallsWire(resp.ToolCalls)
}
out := ChatCompletion{
ID: newID(),
@ -223,7 +284,7 @@ func (g *Gateway) streamChat(w http.ResponseWriter, ctx context.Context, cands [
chunk := ChatChunk{
ID: id, Object: "chat.completion.chunk", Created: created, Model: effective,
}
delta := RespMessage{Content: ck.Content}
delta := RespMessage{Role: "assistant", Content: ck.Content}
if ck.ReasoningContent != "" {
delta.ReasoningContent = ck.ReasoningContent
}
@ -269,7 +330,7 @@ func (g *Gateway) handleImage(w http.ResponseWriter, r *http.Request) {
if model == "" {
model = g.core.DefaultModel()
}
cands, _ := g.resolveCands(model)
cands, _ := g.resolveByModel(model)
cands = imageOnly(cands)
if len(cands) == 0 {
writeError(w, http.StatusServiceUnavailable, "no_provider", "no image source configured")

44
internal/gateway/ui/index.html
View File

@ -155,6 +155,50 @@ html[data-theme="dark"] .dropzone.dragover, html[data-theme="dark"] .dropzone:ho
.empty { color:var(--muted); text-align:center; padding:24px 0; }
#modal-wrap { position:fixed; inset:0; background:rgba(15,22,44,.45); display:flex; align-items:flex-start;
justify-content:center; overflow:auto; padding:48px 20px; z-index:50; }
.twrap { overflow-x:auto; -webkit-overflow-scrolling:touch; }
/* ---------- responsive / narrow screens ---------- */
@media (max-width: 900px) {
header { padding:12px 16px; }
nav { padding:12px 16px 0; overflow-x:auto; }
nav button { padding:7px 12px; white-space:nowrap; }
main { padding:16px 16px 40px; }
.card { padding:16px; }
}
@media (max-width: 640px) {
header { gap:8px; padding:10px 12px; }
.brand h1 { font-size:15px; }
.brand .sub { display:none; }
.hd-actions button { padding:5px 9px; }
nav { gap:4px; padding:10px 12px 0; }
nav button { padding:6px 10px; font-size:13px; }
main { padding:12px 12px 32px; }
.card { padding:13px; border-radius:12px; margin-bottom:14px; }
.card h2 { font-size:13px; }
th,td { padding:8px 10px; }
.row { flex-direction:column; gap:0; }
.model-row { flex-wrap:wrap; }
.model-row input { flex:1 1 120px; }
.model-row select { flex:0 0 auto; }
.tab-chat { height:calc(100vh - 150px); }
.msg { gap:7px; }
.avatar { width:24px; height:24px; font-size:11px; }
.bubble { max-width:90%; padding:8px 11px; font-size:13px; }
.chat-log { padding:14px 12px 6px; gap:14px; }
.chat-tools { flex-wrap:wrap; gap:8px; }
.chat-tools .tl { display:none; }
.chat-tools select { flex:1 1 auto; min-width:0; }
.chat-box { gap:7px; }
.chat-box .sendbtn { padding:10px 13px; }
.attach-btn { width:38px; height:38px; }
.chat-box textarea { font-size:13.5px; }
.chat-composer { padding:8px 9px 10px; }
#modal-wrap { padding:14px 10px; }
.dropzone { padding:18px 14px; }
#toast { left:12px; right:12px; bottom:12px; text-align:center; }
pre.configbox { font-size:11.5px; padding:11px; }
.att img { height:52px; max-width:90px; }
}
</style>
</head>
<body>

29
internal/lua/adapters/anthropic.lua
View File

@ -103,12 +103,41 @@ function adapter.transform_stream_chunk(raw_chunk)
if chunk.type == "message_delta" then
return json.encode({ content = "", done = (chunk.delta and chunk.delta.stop_reason ~= nil) })
end
if chunk.type == "content_block_start" and chunk.content_block
and chunk.content_block.type == "tool_use" then
-- first fragment of a tool call: emit index + id + name, empty args
return json.encode({
content = "", done = false,
tool_calls = { {
index = chunk.index or 0,
id = chunk.content_block.id or "",
type = "function",
["function"] = { name = chunk.content_block.name or "", arguments = "" }
} }
})
end
if chunk.type == "content_block_delta" and chunk.delta then
if chunk.delta.type == "input_json_delta" then
-- incremental JSON fragment; clients accumulate across chunks
local unified = { content = "", done = false, tool_calls = { {
index = chunk.index or 0,
id = "",
type = "function",
["function"] = { name = "", arguments = chunk.delta.partial_json or "" }
} } }
return json.encode(unified)
end
if chunk.delta.type == "thinking_delta" and chunk.delta.thinking then
return json.encode({ content = "", done = false, reasoning_content = chunk.delta.thinking })
end
return json.encode({ content = chunk.delta.text or "", done = false })
end
if chunk.type == "message_stop" then
return json.encode({ content = "", done = true })
end
if chunk.type == "content_block_stop" then
return json.encode({ content = "", done = false })
end
return ""
end

24
internal/lua/adapters/deepseek.lua
View File

@ -20,6 +20,18 @@ function adapter.transform_request(raw_body)
req.extra_body.thinking = { type = "disabled" }
end
req.disable_thinking = nil
-- V4 thinking 模式要求：带 tool_calls 的 assistant 消息必须回传 reasoning_content。
-- OpenAI 兼容客户端不会发该字段，补空串即可通过校验。
if req.messages then
for _, msg in ipairs(req.messages) do
if msg.role == "assistant" and msg.tool_calls and msg.tool_calls[1] then
if msg.reasoning_content == nil then
msg.reasoning_content = ""
end
end
end
end
return json.encode(req)
end
@ -73,10 +85,18 @@ function adapter.transform_stream_chunk(raw_chunk)
if not chunk.choices or #chunk.choices == 0 then return "" end
local delta = chunk.choices[1].delta or {}
local fr = chunk.choices[1].finish_reason
return json.encode({
local unified = {
content = delta.content or "",
done = (fr ~= nil)
})
}
if delta.reasoning_content then
unified.reasoning_content = delta.reasoning_content
end
if delta.tool_calls then
unified.tool_calls = delta.tool_calls
end
return json.encode(unified)
end
return adapter

27
internal/lua/adapters/gemini.lua
View File

@ -93,16 +93,31 @@ function adapter.transform_stream_chunk(raw_chunk)
if not chunk.candidates or #chunk.candidates == 0 then return "" end
local cand = chunk.candidates[1]
local content = ""
local unified = { content = "", done = (cand.finishReason ~= nil) }
local reasoning = ""
local tools = {}
if cand.content and cand.content.parts then
for _, part in ipairs(cand.content.parts) do
content = content .. (part.text or "")
if part.text then
unified.content = (unified.content or "") .. part.text
elseif part.reasoning_content then
reasoning = reasoning .. part.reasoning_content
elseif part.functionCall then
table.insert(tools, {
index = #tools,
id = part.functionCall.id or ("call_" .. #tools),
type = "function",
["function"] = {
name = part.functionCall.name or "",
arguments = part.functionCall.args or "{}"
}
})
end
end
end
return json.encode({
content = content,
done = (cand.finishReason ~= nil)
})
if reasoning ~= "" then unified.reasoning_content = reasoning end
if #tools > 0 then unified.tool_calls = tools end
return json.encode(unified)
end
return adapter

12
internal/lua/adapters/github.lua
View File

@ -66,10 +66,18 @@ function adapter.transform_stream_chunk(raw_chunk)
if not chunk.choices or #chunk.choices == 0 then return "" end
local delta = chunk.choices[1].delta or {}
local fr = chunk.choices[1].finish_reason
return json.encode({
local unified = {
content = delta.content or "",
done = (fr ~= nil)
})
}
if delta.reasoning_content then
unified.reasoning_content = delta.reasoning_content
end
if delta.tool_calls then
unified.tool_calls = delta.tool_calls
end
return json.encode(unified)
end
return adapter

12
internal/lua/adapters/groq.lua
View File

@ -65,10 +65,18 @@ function adapter.transform_stream_chunk(raw_chunk)
if not chunk.choices or #chunk.choices == 0 then return "" end
local delta = chunk.choices[1].delta or {}
local fr = chunk.choices[1].finish_reason
return json.encode({
local unified = {
content = delta.content or "",
done = (fr ~= nil)
})
}
if delta.reasoning_content then
unified.reasoning_content = delta.reasoning_content
end
if delta.tool_calls then
unified.tool_calls = delta.tool_calls
end
return json.encode(unified)
end
return adapter

12
internal/lua/adapters/kimicode.lua
View File

@ -98,10 +98,18 @@ function adapter.transform_stream_chunk(raw_chunk)
if not chunk.choices or #chunk.choices == 0 then return "" end
local delta = chunk.choices[1].delta or {}
local fr = chunk.choices[1].finish_reason
return json.encode({
local unified = {
content = delta.content or "",
done = (fr ~= nil)
})
}
if delta.reasoning_content then
unified.reasoning_content = delta.reasoning_content
end
if delta.tool_calls then
unified.tool_calls = delta.tool_calls
end
return json.encode(unified)
end
return adapter

12
internal/lua/adapters/mistral.lua
View File

@ -65,10 +65,18 @@ function adapter.transform_stream_chunk(raw_chunk)
if not chunk.choices or #chunk.choices == 0 then return "" end
local delta = chunk.choices[1].delta or {}
local fr = chunk.choices[1].finish_reason
return json.encode({
local unified = {
content = delta.content or "",
done = (fr ~= nil)
})
}
if delta.reasoning_content then
unified.reasoning_content = delta.reasoning_content
end
if delta.tool_calls then
unified.tool_calls = delta.tool_calls
end
return json.encode(unified)
end
return adapter

23
internal/lua/adapters/ollama.lua
View File

@ -72,10 +72,29 @@ function adapter.transform_stream_chunk(raw_chunk)
if not ok then return "" end
if not chunk.message then return "" end
return json.encode({
local unified = {
content = chunk.message.content or "",
done = chunk.done or false
})
}
if chunk.message.reasoning_content then
unified.reasoning_content = chunk.message.reasoning_content
end
if chunk.message.tool_calls then
local tools = {}
for _, tc in ipairs(chunk.message.tool_calls) do
table.insert(tools, {
index = #tools,
id = tc.id or ("call_" .. #tools),
type = "function",
["function"] = {
name = tc["function"] and tc["function"].name or "",
arguments = tc["function"] and (tc["function"].arguments or "{}") or "{}"
}
})
end
unified.tool_calls = tools
end
return json.encode(unified)
end
return adapter

12
internal/lua/adapters/openai.lua
View File

@ -71,10 +71,18 @@ function adapter.transform_stream_chunk(raw_chunk)
local delta = chunk.choices[1].delta or {}
local fr = chunk.choices[1].finish_reason
return json.encode({
local unified = {
content = delta.content or "",
done = (fr ~= nil)
})
}
if delta.reasoning_content then
unified.reasoning_content = delta.reasoning_content
end
if delta.tool_calls then
-- pass raw streaming fragments through; OpenAI clients accumulate index+id+name+arguments
unified.tool_calls = delta.tool_calls
end
return json.encode(unified)
end
return adapter

37
internal/provider/provider.go
View File

@ -100,6 +100,43 @@ func (p *Provider) ModelByID(id string) *config.Model {
return nil
}
// ModelFor resolves the model name this provider should send upstream.
// If the requested model is not owned by this provider (e.g. an AUTO chain
// fallback), it returns this provider's highest-priority chat model instead.
func (p *Provider) ModelFor(reqModel string) string {
if reqModel == "" || isAutoID(reqModel) {
return p.bestChatModel()
}
if p.ModelByID(reqModel) != nil {
return reqModel
}
return p.bestChatModel()
}
// bestChatModel returns the highest-priority chat-kind model of this source.
func (p *Provider) bestChatModel() string {
bestID, bestPrio := "", -1
for _, m := range p.cfg.Models {
if m.Kind != "" && m.Kind != "chat" {
continue
}
if m.Priority > bestPrio {
bestPrio = m.Priority
bestID = m.ID
}
}
if bestID == "" && len(p.cfg.Models) > 0 {
bestID = p.cfg.Models[0].ID
}
return bestID
}
// IsAutoID reports whether s is an AUTO routing placeholder.
func isAutoID(s string) bool {
s = strings.TrimSpace(s)
return s == "" || strings.EqualFold(s, "AUTO")
}
// Endpoint resolves the upstream chat path.
func (p *Provider) Endpoint() string {
if p.cfg.Endpoint != "" {

17
internal/scheduler/scheduler.go
View File

@ -28,6 +28,7 @@ func New(maxRetries int) *Scheduler {
type Provider interface {
Name() string
Available() bool
ModelFor(reqModel string) string
Chat(ctx context.Context, req *types.ChatRequest) (*types.UnifiedResponse, error)
ChatStream(ctx context.Context, req *types.ChatRequest) (<-chan types.UnifiedChunk, error)
Image(ctx context.Context, req *types.ImageGenRequest) (*types.UnifiedResponse, error)
@ -42,13 +43,18 @@ func FromRegistry(ps []*provider.Provider) []Provider {
return out
}
// Chat runs a chat request across cands, falling back on failure.
// Chat runs a chat request across cands, falling back on failure. Each
// candidate receives a request pinned to its own model (ModelFor), so an AUTO
// chain fallback switches the model id per provider instead of reusing the
// first candidate's model name.
func (s *Scheduler) Chat(ctx context.Context, cands []Provider, req *types.ChatRequest) (*types.UnifiedResponse, error) {
attempts := s.MaxRetries + 1
var lastErr error
for i := 0; i < attempts && i < len(cands); i++ {
p := cands[i]
resp, err := p.Chat(ctx, req)
r := *req
r.Model = p.ModelFor(req.Model)
resp, err := p.Chat(ctx, &r)
if ctx.Err() != nil {
return nil, ctx.Err()
}
@ -68,13 +74,16 @@ func (s *Scheduler) Chat(ctx context.Context, cands []Provider, req *types.ChatR
return nil, lastErr
}
// ChatStream runs a streaming chat across cands, falling back early on connect errors.
// ChatStream runs a streaming chat across cands, falling back early on connect
// errors. The request model is pinned per candidate like Chat.
func (s *Scheduler) ChatStream(ctx context.Context, cands []Provider, req *types.ChatRequest) (<-chan types.UnifiedChunk, error) {
attempts := s.MaxRetries + 1
var lastErr error
for i := 0; i < attempts && i < len(cands); i++ {
p := cands[i]
resp, err := p.ChatStream(ctx, req)
r := *req
r.Model = p.ModelFor(req.Model)
resp, err := p.ChatStream(ctx, &r)
if err == nil {
return resp, nil
}

13
internal/types/types.go
View File

@ -47,7 +47,7 @@ type ChatMessage struct {
Content json.RawMessage `json:"content,omitempty"`
ReasoningContent string `json:"reasoning_content,omitempty"`
ToolCallID string `json:"tool_call_id,omitempty"`
ToolCalls []ToolCall `json:"tool_calls,omitempty"`
ToolCalls json.RawMessage `json:"tool_calls,omitempty"`
}
func StringContent(s string) json.RawMessage { b, _ := json.Marshal(s); return b }
@ -100,11 +100,14 @@ type ImageGenResponse struct {
// ---- Unified streaming chunk produced by adapters ----
// UnifiedChunk is one streamed delta. ToolCalls carries the raw upstream
// streaming tool_calls array (incremental fragments with an index field), which
// OpenAI-compatible clients accumulate themselves.
type UnifiedChunk struct {
Content string `json:"content"`
Done bool `json:"done"`
ToolCalls []ToolCall `json:"tool_calls,omitempty"`
ReasoningContent string `json:"reasoning_content,omitempty"`
Content string `json:"content"`
Done bool `json:"done"`
ToolCalls json.RawMessage `json:"tool_calls,omitempty"`
ReasoningContent string `json:"reasoning_content,omitempty"`
}
// Meta passed to Lua build_headers hook