Files
picoclaw/web/backend/api/models.go
T
wenjie e55b3b7a8d feat(web): migrate launcher to modular web frontend/backend and improve management UX (#1275)
* refactor: remove the legacy picoclaw-launcher

* feat: create initial web frontend and backend structure

* feat(packaging): add desktop entry for PicoClaw Launcher (#1062)

- Add .desktop file with Terminal=true, named "PicoClaw Launcher"
- Install to /usr/share/applications/ for app menu visibility
- Add 512x512 PNG icon to /usr/share/icons/hicolor/

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>

* `make dev`: If you haven't built it before, you need to run `build` first.

* feat(web): comprehensive web UI and backend refactoring
This commit introduces a major overhaul of both the frontend web UI and the Go backend API, transitioning to a highly modular architecture and integrating new core features.
Backend:
- Refactored monolithic API endpoints into domain-specific modules (config, gateway, log, models, pico, session).
- Cleaned up obsolete files (`server.go`, `status.go`, WebSocket handlers) and outdated tests.
- Implemented Gateway process lifecycle management (start/stop/restart) and real-time log streaming.
Frontend:
- Integrated Shadcn UI components to establish a modern, consistent design system.
- Introduced a new application layout featuring a responsive sidebar (`app-sidebar`) and header.
- Implemented internationalization (i18n) with initial support for English and Chinese.
- Restructured API clients, hooks, and Zustand stores into logical domains.
- Added new management pages for Settings, Logs, Models, Providers, and Credentials.
- Upgraded the Pico chat interface with session history management and dynamic model selection.
Build & Config:
- Updated frontend dependencies, Vite configuration, and lockfiles.
- Refined routing setup and overarching application stylesheets.

* feat(web): enhance model management, sorting, and deletion logic
- Implement model sorting in UI (default > configured > unconfigured)
- Prevent deletion of default models in the frontend
- Update backend to clear default settings when a model is deleted
- Add existence validation when setting a default model via API
- Group models in chat UI by type (API Key, OAuth, Local)
- Conditionally display model selector in chat based on configuration status

* refactor(web): refactor chat page into modular components/hooks and update i18n

- split chat route into dedicated chat components (page, composer, empty state, messages, history, model selector)
- extract model/session logic into use-chat-models and use-session-history hooks
- update chat locale keys in en/zh and add empty-state/history-related translations

* refactor(models): refactor models page into modular components and improve UX

- split /models route into dedicated components (page, provider section, card, add/edit sheets, delete dialog)
- add provider grouping/sorting, provider labels/icons, and a no-default hint in the models page
- add "Set as default model" toggle to add/edit flows with safer defaults
- introduce shared form helpers and new UI primitives (field, label, switch)
- update i18n strings (en/zh) for models and gateway header text usage
- apply minor UI polish (models nav icon, separator client directive)

* fix(web): add SPA index fallback for embedded frontend routes

Serve existing static assets as-is, keep /api/* and missing asset paths returning 404, and add tests for SPA fallback behavior on refresh.

* fix(frontend/chat): normalize message timestamp units to prevent invalid far-future dates

* chore: delete TestSPARouteFallsBackToIndex

* feat: update build for web-based launcher (#1186)

- Makefile: add build-launcher target (builds frontend + Go backend)
- GoReleaser: point picoclaw-launcher build to web/backend, add frontend
  build hook, restore winres hook with updated paths
- Restore icon.ico and winres config from main for Windows builds

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>

* feat(credentials): add multi-provider OAuth credential management

- add backend `/api/oauth/*` endpoints for provider status, browser/device-code/token login, flow query/polling, and logout
- extend API handler with OAuth flow/state tracking and route registration, plus OAuth unit tests
- implement frontend credentials page/components for OpenAI, Anthropic, and Google Antigravity login/logout
- add OAuth API client and `useCredentialsPage` hook, with new EN/ZH i18n strings

* chore: remove placeholder index.html from dist (#1188)

The .gitkeep is sufficient for go:embed to find the dist directory.

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>

* fix(frontend): polish model and credential UX; remove Providers nav

- remove the Providers item from sidebar navigation and locale keys
- simplify chat composer by dropping attach/voice action buttons
- support ReactNode titles in credential cards and add provider brand icons
- refine sheet header/footer styling and device-code footer button hierarchy
- disable “Set default” when a model is unconfigured or already default

* feat(web): Update  config page (#1173)

* feat(web): Update  config page

* fix(web): useEffect resets editorValue whenever config changes

* fix(web): react-hooks/set-state-in-effect error & pnpm lint #1173

* feat(web): add channel management page for web console (#1190)

* feat(web): add channel management page for web console

Add a complete channel management UI that allows users to configure
messaging channels (Telegram, Discord, Slack, Feishu, etc.) directly
from the web console instead of manually editing config.json.

Backend: GET/PUT/PATCH API endpoints for listing, updating, and
toggling channels with secret field masking.

Frontend: Channel cards grid with enable/disable toggles, per-channel
configuration sheets with dedicated forms for major platforms and a
generic fallback for others.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix(web/channels): move channels to own sidebar group and fix sheet padding

- Channels now has its own navigation group instead of being under Services
- Fix edit sheet form content padding (px-1 -> px-4) to match header/footer
- Fix naked return lint error in extractChannelInfo

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>

* fix(web): harden channel config updates and resolve frontend lint issues

- validate channel PUT/PATCH updates before saving and return structured validation errors
- require `enabled` in toggle requests to avoid silent false defaults
- support editing `allow_origins` in the generic channel form and parse string/array inputs on backend
- replace channel form `any` usage with `ChannelConfig` (`Record<string, unknown>`) and add safe value helpers
- add i18n strings for allow-origins fields and apply related frontend formatting cleanups

* fix(frontend): prevent false "Invalid JSON" errors in config editor

* feat: add startup readiness checks and propagate start availability to UI

- add gateway precondition validation for default model and credentials
- auto-start gateway on backend boot when conditions are met
- include gateway_start_allowed and gateway_start_reason in status updates
- prevent frontend start actions when gateway cannot be started

* feat(web): revamp channel config UX with catalog-based routing

- replace legacy channel management endpoints with a backend channel catalog API
- switch frontend channel updates to PATCH /api/config and per-channel config pages
- add dynamic channel items in the sidebar with support for expand/collapse
- migrate /channels to nested routes (/channels/$name) and remove old card/sheet flow
- improve channel forms with clearer hints, required/error states, and reusable switch cards
- fix Discord mention-only toggle to read/write group_trigger.mention_only

* refactor(frontend): move shared-form to components and unify default-model switch with SwitchCardField

* fix(frontend): improve model form validation and unify secret placeholder handling

- block duplicate model aliases when adding a model (with localized error messages)
- share masked secret placeholder logic across model and channel forms
- refresh gateway state after setting the default model
- apply minor UI cleanup to provider icon rendering

* feat(web): add visual system config and launcher/autostart controls

- add launcher config model and persistence (`launcher-config.json`) for port/public/CIDR settings
- add system APIs for launch-at-login and launcher parameters
- apply CIDR-based access-control middleware to backend HTTP routes
- split config routing into visual config and raw JSON config pages
- add frontend system API client and visual config sections for runtime/devices/launcher
- expand i18n strings (en/zh) for new config UI
- improve sidebar active matching and session ID generation fallback

* refactor(frontend): remove i18n fallback strings and drop providers route

- Replace `t(key, defaultValue)` calls with key-only translations across UI pages
- Clean up locale files by pruning unused keys and adding missing shared keys
- Remove the obsolete `/providers` page and update generated route tree

* fix(backend): correct gateway status detection on Windows

* fix(repo): keep web backend dist placeholder tracked

---------

Co-authored-by: Guoguo <16666742+imguoguo@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Dihubopen <dihubcn@gmail.com>
Co-authored-by: Dihubopen <130813726+Dihubopen@users.noreply.github.com>
2026-03-09 19:42:03 +08:00

299 lines
8.8 KiB
Go

package api
import (
"encoding/json"
"fmt"
"io"
"net/http"
"strconv"
"github.com/sipeed/picoclaw/pkg/config"
)
// registerModelRoutes binds model list management endpoints to the ServeMux.
func (h *Handler) registerModelRoutes(mux *http.ServeMux) {
mux.HandleFunc("GET /api/models", h.handleListModels)
mux.HandleFunc("POST /api/models", h.handleAddModel)
mux.HandleFunc("POST /api/models/default", h.handleSetDefaultModel)
mux.HandleFunc("PUT /api/models/{index}", h.handleUpdateModel)
mux.HandleFunc("DELETE /api/models/{index}", h.handleDeleteModel)
}
// modelResponse is the JSON structure returned for each model in the list.
// All ModelConfig fields are included so the frontend can display and edit them.
type modelResponse struct {
Index int `json:"index"`
ModelName string `json:"model_name"`
Model string `json:"model"`
APIBase string `json:"api_base,omitempty"`
APIKey string `json:"api_key"`
Proxy string `json:"proxy,omitempty"`
AuthMethod string `json:"auth_method,omitempty"`
// Advanced fields
ConnectMode string `json:"connect_mode,omitempty"`
Workspace string `json:"workspace,omitempty"`
RPM int `json:"rpm,omitempty"`
MaxTokensField string `json:"max_tokens_field,omitempty"`
RequestTimeout int `json:"request_timeout,omitempty"`
ThinkingLevel string `json:"thinking_level,omitempty"`
// Meta
Configured bool `json:"configured"`
IsDefault bool `json:"is_default"`
}
// handleListModels returns all model_list entries with masked API keys.
//
// GET /api/models
func (h *Handler) handleListModels(w http.ResponseWriter, r *http.Request) {
cfg, err := h.loadFilteredConfig()
if err != nil {
http.Error(w, fmt.Sprintf("Failed to load config: %v", err), http.StatusInternalServerError)
return
}
defaultModel := cfg.Agents.Defaults.GetModelName()
models := make([]modelResponse, 0, len(cfg.ModelList))
for i, m := range cfg.ModelList {
models = append(models, modelResponse{
Index: i,
ModelName: m.ModelName,
Model: m.Model,
APIBase: m.APIBase,
APIKey: maskAPIKey(m.APIKey),
Proxy: m.Proxy,
AuthMethod: m.AuthMethod,
ConnectMode: m.ConnectMode,
Workspace: m.Workspace,
RPM: m.RPM,
MaxTokensField: m.MaxTokensField,
RequestTimeout: m.RequestTimeout,
ThinkingLevel: m.ThinkingLevel,
Configured: m.APIKey != "" || m.AuthMethod != "",
IsDefault: m.ModelName == defaultModel,
})
}
w.Header().Set("Content-Type", "application/json")
json.NewEncoder(w).Encode(map[string]any{
"models": models,
"total": len(models),
"default_model": defaultModel,
})
}
// handleAddModel appends a new model configuration entry.
//
// POST /api/models
func (h *Handler) handleAddModel(w http.ResponseWriter, r *http.Request) {
body, err := io.ReadAll(io.LimitReader(r.Body, 1<<20))
if err != nil {
http.Error(w, "Failed to read request body", http.StatusBadRequest)
return
}
defer r.Body.Close()
var mc config.ModelConfig
if err = json.Unmarshal(body, &mc); err != nil {
http.Error(w, fmt.Sprintf("Invalid JSON: %v", err), http.StatusBadRequest)
return
}
if err = mc.Validate(); err != nil {
http.Error(w, fmt.Sprintf("Validation error: %v", err), http.StatusBadRequest)
return
}
cfg, err := config.LoadConfig(h.configPath)
if err != nil {
http.Error(w, fmt.Sprintf("Failed to load config: %v", err), http.StatusInternalServerError)
return
}
cfg.ModelList = append(cfg.ModelList, mc)
if err := config.SaveConfig(h.configPath, cfg); err != nil {
http.Error(w, fmt.Sprintf("Failed to save config: %v", err), http.StatusInternalServerError)
return
}
w.Header().Set("Content-Type", "application/json")
json.NewEncoder(w).Encode(map[string]any{
"status": "ok",
"index": len(cfg.ModelList) - 1,
})
}
// handleUpdateModel replaces a model configuration entry at the given index.
// If the request body omits api_key (or sends an empty string), the existing
// stored key is preserved so callers can update only api_base / proxy without
// exposing or clearing the secret.
//
// PUT /api/models/{index}
func (h *Handler) handleUpdateModel(w http.ResponseWriter, r *http.Request) {
idx, err := strconv.Atoi(r.PathValue("index"))
if err != nil {
http.Error(w, "Invalid index", http.StatusBadRequest)
return
}
body, err := io.ReadAll(io.LimitReader(r.Body, 1<<20))
if err != nil {
http.Error(w, "Failed to read request body", http.StatusBadRequest)
return
}
defer r.Body.Close()
var mc config.ModelConfig
if err = json.Unmarshal(body, &mc); err != nil {
http.Error(w, fmt.Sprintf("Invalid JSON: %v", err), http.StatusBadRequest)
return
}
if err = mc.Validate(); err != nil {
http.Error(w, fmt.Sprintf("Validation error: %v", err), http.StatusBadRequest)
return
}
cfg, err := config.LoadConfig(h.configPath)
if err != nil {
http.Error(w, fmt.Sprintf("Failed to load config: %v", err), http.StatusInternalServerError)
return
}
if idx < 0 || idx >= len(cfg.ModelList) {
http.Error(w, fmt.Sprintf("Index %d out of range (0-%d)", idx, len(cfg.ModelList)-1), http.StatusNotFound)
return
}
// Preserve the existing API key when the caller omits it (empty string).
// This lets the UI update api_base / proxy without clearing the stored secret.
if mc.APIKey == "" {
mc.APIKey = cfg.ModelList[idx].APIKey
}
cfg.ModelList[idx] = mc
if err := config.SaveConfig(h.configPath, cfg); err != nil {
http.Error(w, fmt.Sprintf("Failed to save config: %v", err), http.StatusInternalServerError)
return
}
w.Header().Set("Content-Type", "application/json")
json.NewEncoder(w).Encode(map[string]string{"status": "ok"})
}
// handleDeleteModel removes a model configuration entry at the given index.
//
// DELETE /api/models/{index}
func (h *Handler) handleDeleteModel(w http.ResponseWriter, r *http.Request) {
idx, err := strconv.Atoi(r.PathValue("index"))
if err != nil {
http.Error(w, "Invalid index", http.StatusBadRequest)
return
}
cfg, err := config.LoadConfig(h.configPath)
if err != nil {
http.Error(w, fmt.Sprintf("Failed to load config: %v", err), http.StatusInternalServerError)
return
}
if idx < 0 || idx >= len(cfg.ModelList) {
http.Error(w, fmt.Sprintf("Index %d out of range (0-%d)", idx, len(cfg.ModelList)-1), http.StatusNotFound)
return
}
deletedModelName := cfg.ModelList[idx].ModelName
cfg.ModelList = append(cfg.ModelList[:idx], cfg.ModelList[idx+1:]...)
// If the deleted model was the default, clear it.
if cfg.Agents.Defaults.ModelName == deletedModelName {
cfg.Agents.Defaults.ModelName = ""
}
if cfg.Agents.Defaults.Model == deletedModelName {
cfg.Agents.Defaults.Model = ""
}
if err := config.SaveConfig(h.configPath, cfg); err != nil {
http.Error(w, fmt.Sprintf("Failed to save config: %v", err), http.StatusInternalServerError)
return
}
w.Header().Set("Content-Type", "application/json")
json.NewEncoder(w).Encode(map[string]string{"status": "ok"})
}
// handleSetDefaultModel sets the default model for all agents.
//
// POST /api/models/default
func (h *Handler) handleSetDefaultModel(w http.ResponseWriter, r *http.Request) {
body, err := io.ReadAll(io.LimitReader(r.Body, 1<<20))
if err != nil {
http.Error(w, "Failed to read request body", http.StatusBadRequest)
return
}
defer r.Body.Close()
var req struct {
ModelName string `json:"model_name"`
}
if err = json.Unmarshal(body, &req); err != nil {
http.Error(w, fmt.Sprintf("Invalid JSON: %v", err), http.StatusBadRequest)
return
}
if req.ModelName == "" {
http.Error(w, "model_name is required", http.StatusBadRequest)
return
}
cfg, err := config.LoadConfig(h.configPath)
if err != nil {
http.Error(w, fmt.Sprintf("Failed to load config: %v", err), http.StatusInternalServerError)
return
}
// Verify the model_name exists in model_list
found := false
for _, m := range cfg.ModelList {
if m.ModelName == req.ModelName {
found = true
break
}
}
if !found {
http.Error(w, fmt.Sprintf("Model %q not found in model_list", req.ModelName), http.StatusNotFound)
return
}
cfg.Agents.Defaults.ModelName = req.ModelName
if err := config.SaveConfig(h.configPath, cfg); err != nil {
http.Error(w, fmt.Sprintf("Failed to save config: %v", err), http.StatusInternalServerError)
return
}
w.Header().Set("Content-Type", "application/json")
json.NewEncoder(w).Encode(map[string]string{
"status": "ok",
"default_model": req.ModelName,
})
}
// maskAPIKey returns a masked version of an API key for safe display.
// Keys longer than 8 chars show prefix + last 4 chars: "sk-****abcd"
// Shorter keys are fully masked as "****".
// Empty keys return empty string.
func maskAPIKey(key string) string {
if key == "" {
return ""
}
if len(key) <= 8 {
return "****"
}
// Show first 3 chars and last 4 chars
return key[:3] + "****" + key[len(key)-4:]
}