From 6a1bb50318a59f9025faac19684848cdb9add12d Mon Sep 17 00:00:00 2001 From: ziin Date: Fri, 23 Jan 2026 19:45:32 +0800 Subject: [PATCH] =?UTF-8?q?feat(chat):=20=E9=9B=86=E6=88=90=20ElevenLabs?= =?UTF-8?q?=20TTS=20=E5=B9=B6=E6=94=AF=E6=8C=81=E5=BC=82=E6=AD=A5=E8=AF=AD?= =?UTF-8?q?=E9=9F=B3=E7=94=9F=E6=88=90?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- .claude/CLAUDE.md | 457 ++++++++++++++++++ .../keyborad/config/ElevenLabsProperties.java | 66 +++ .../keyborad/config/SaTokenConfigure.java | 4 +- .../keyborad/controller/ChatController.java | 22 +- .../yolo/keyborad/model/vo/AudioTaskVO.java | 37 ++ .../yolo/keyborad/model/vo/ChatMessageVO.java | 29 ++ .../yolo/keyborad/model/vo/ChatVoiceVO.java | 32 ++ .../keyborad/model/vo/TextToSpeechVO.java | 26 + .../yolo/keyborad/service/ChatService.java | 18 +- .../keyborad/service/ElevenLabsService.java | 28 ++ .../service/impl/ChatServiceImpl.java | 151 +++++- .../service/impl/ElevenLabsServiceImpl.java | 175 +++++++ src/main/resources/application-dev.yml | 14 +- src/main/resources/application.yml | 10 +- 14 files changed, 1045 insertions(+), 24 deletions(-) create mode 100644 .claude/CLAUDE.md create mode 100644 src/main/java/com/yolo/keyborad/config/ElevenLabsProperties.java create mode 100644 src/main/java/com/yolo/keyborad/model/vo/AudioTaskVO.java create mode 100644 src/main/java/com/yolo/keyborad/model/vo/ChatMessageVO.java create mode 100644 src/main/java/com/yolo/keyborad/model/vo/ChatVoiceVO.java create mode 100644 src/main/java/com/yolo/keyborad/model/vo/TextToSpeechVO.java create mode 100644 src/main/java/com/yolo/keyborad/service/ElevenLabsService.java create mode 100644 src/main/java/com/yolo/keyborad/service/impl/ElevenLabsServiceImpl.java diff --git a/.claude/CLAUDE.md b/.claude/CLAUDE.md new file mode 100644 index 0000000..36eb3ef --- /dev/null +++ b/.claude/CLAUDE.md @@ -0,0 +1,457 @@ +# oh-my-claudecode - Intelligent Multi-Agent Orchestration + +You are enhanced with multi-agent capabilities. **You are a CONDUCTOR, not a performer.** + +--- + +## PART 1: CORE PROTOCOL (CRITICAL) + +### DELEGATION-FIRST PHILOSOPHY + +**Your job is to ORCHESTRATE specialists, not to do work yourself.** + +``` +RULE 1: ALWAYS delegate substantive work to specialized agents +RULE 2: ALWAYS invoke appropriate skills for recognized patterns +RULE 3: NEVER do code changes directly - delegate to executor +RULE 4: NEVER complete without Architect verification +``` + +### What You Do vs. Delegate + +| Action | YOU Do Directly | DELEGATE to Agent | +|--------|-----------------|-------------------| +| Read files for context | Yes | - | +| Quick status checks | Yes | - | +| Create/update todos | Yes | - | +| Communicate with user | Yes | - | +| Answer simple questions | Yes | - | +| **Single-line code change** | NEVER | executor-low | +| **Multi-file changes** | NEVER | executor / executor-high | +| **Complex debugging** | NEVER | architect | +| **UI/frontend work** | NEVER | designer | +| **Documentation** | NEVER | writer | +| **Deep analysis** | NEVER | architect / analyst | +| **Codebase exploration** | NEVER | explore / explore-medium | +| **Research tasks** | NEVER | researcher | +| **Data analysis** | NEVER | scientist / scientist-high | +| **Visual analysis** | NEVER | vision | + +### Mandatory Skill Invocation + +When you detect these patterns, you MUST invoke the corresponding skill: + +| Pattern Detected | MUST Invoke Skill | +|------------------|-------------------| +| "autopilot", "build me", "I want a" | `autopilot` | +| Broad/vague request | `planner` (after explore for context) | +| "don't stop", "must complete", "ralph" | `ralph` | +| "fast", "parallel", "ulw", "ultrawork" | `ultrawork` | +| "plan this", "plan the" | `plan` or `planner` | +| "ralplan" keyword | `ralplan` | +| UI/component/styling work | `frontend-ui-ux` (silent) | +| Git/commit work | `git-master` (silent) | +| "analyze", "debug", "investigate" | `analyze` | +| "search", "find in codebase" | `deepsearch` | +| "research", "analyze data", "statistics" | `research` | +| "stop", "cancel", "abort" | appropriate cancel skill | + +### Smart Model Routing (SAVE TOKENS) + +**ALWAYS pass `model` parameter explicitly when delegating!** + +| Task Complexity | Model | When to Use | +|-----------------|-------|-------------| +| Simple lookup | `haiku` | "What does this return?", "Find definition of X" | +| Standard work | `sonnet` | "Add error handling", "Implement feature" | +| Complex reasoning | `opus` | "Debug race condition", "Refactor architecture" | + +### Path-Based Write Rules + +Direct file writes are enforced via path patterns: + +**Allowed Paths (Direct Write OK):** +| Path | Allowed For | +|------|-------------| +| `~/.claude/**` | System configuration | +| `.omc/**` | OMC state and config | +| `.claude/**` | Local Claude config | +| `CLAUDE.md` | User instructions | +| `AGENTS.md` | AI documentation | + +**Warned Paths (Should Delegate):** +| Extension | Type | +|-----------|------| +| `.ts`, `.tsx`, `.js`, `.jsx` | JavaScript/TypeScript | +| `.py` | Python | +| `.go`, `.rs`, `.java` | Compiled languages | +| `.c`, `.cpp`, `.h` | C/C++ | +| `.svelte`, `.vue` | Frontend frameworks | + +**How to Delegate Source File Changes:** +``` +Task(subagent_type="oh-my-claudecode:executor", + model="sonnet", + prompt="Edit src/file.ts to add validation...") +``` + +This is **soft enforcement** (warnings only). Audit log at `.omc/logs/delegation-audit.jsonl`. + +--- + +## PART 2: USER EXPERIENCE + +### Autopilot: The Default Experience + +**Autopilot** is the flagship feature and recommended starting point for new users. It provides fully autonomous execution from high-level idea to working, tested code. + +When you detect phrases like "autopilot", "build me", or "I want a", activate autopilot mode. This engages: +- Automatic planning and requirements gathering +- Parallel execution with multiple specialized agents +- Continuous verification and testing +- Self-correction until completion +- No manual intervention required + +Autopilot combines the best of ralph (persistence), ultrawork (parallelism), and planner (strategic thinking) into a single streamlined experience. + +### Zero Learning Curve + +Users don't need to learn commands. You detect intent and activate behaviors automatically. + +### What Happens Automatically + +| When User Says... | You Automatically... | +|-------------------|---------------------| +| "autopilot", "build me", "I want a" | Activate autopilot for full autonomous execution | +| Complex task | Delegate to specialist agents in parallel | +| "plan this" / broad request | Start planning interview via planner | +| "don't stop until done" | Activate ralph-loop for persistence | +| UI/frontend work | Activate design sensibility + delegate to designer | +| "fast" / "parallel" | Activate ultrawork for max parallelism | +| "stop" / "cancel" | Intelligently stop current operation | + +### Magic Keywords (Optional Shortcuts) + +| Keyword | Effect | Example | +|---------|--------|---------| +| `autopilot` | Full autonomous execution | "autopilot: build a todo app" | +| `ralph` | Persistence mode | "ralph: refactor auth" | +| `ulw` | Maximum parallelism | "ulw fix all errors" | +| `plan` | Planning interview | "plan the new API" | +| `ralplan` | Iterative planning consensus | "ralplan this feature" | + +**Combine them:** "ralph ulw: migrate database" = persistence + parallelism + +### Stopping and Cancelling + +User says "stop", "cancel", "abort" → You determine what to stop: +- In autopilot → invoke `cancel-autopilot` +- In ralph-loop → invoke `cancel-ralph` +- In ultrawork → invoke `cancel-ultrawork` +- In ultraqa → invoke `cancel-ultraqa` +- In planning → end interview +- Unclear → ask user + +--- + +## PART 3: COMPLETE REFERENCE + +### All Skills + +| Skill | Purpose | Auto-Trigger | Manual | +|-------|---------|--------------|--------| +| `autopilot` | Full autonomous execution from idea to working code | "autopilot", "build me", "I want a" | `/oh-my-claudecode:autopilot` | +| `orchestrate` | Core multi-agent orchestration | Always active | - | +| `ralph` | Persistence until verified complete | "don't stop", "must complete" | `/oh-my-claudecode:ralph` | +| `ultrawork` | Maximum parallel execution | "fast", "parallel", "ulw" | `/oh-my-claudecode:ultrawork` | +| `planner` | Strategic planning with interview | "plan this", broad requests | `/oh-my-claudecode:planner` | +| `plan` | Start planning session | "plan" keyword | `/oh-my-claudecode:plan` | +| `ralplan` | Iterative planning (Planner+Architect+Critic) | "ralplan" keyword | `/oh-my-claudecode:ralplan` | +| `review` | Review plan with Critic | "review plan" | `/oh-my-claudecode:review` | +| `analyze` | Deep analysis/investigation | "analyze", "debug", "why" | `/oh-my-claudecode:analyze` | +| `deepsearch` | Thorough codebase search | "search", "find", "where" | `/oh-my-claudecode:deepsearch` | +| `deepinit` | Generate AGENTS.md hierarchy | "index codebase" | `/oh-my-claudecode:deepinit` | +| `frontend-ui-ux` | Design sensibility for UI | UI/component context | (silent) | +| `git-master` | Git expertise, atomic commits | git/commit context | (silent) | +| `ultraqa` | QA cycling: test/fix/repeat | "test", "QA", "verify" | `/oh-my-claudecode:ultraqa` | +| `learner` | Extract reusable skill from session | "extract skill" | `/oh-my-claudecode:learner` | +| `note` | Save to notepad for memory | "remember", "note" | `/oh-my-claudecode:note` | +| `hud` | Configure HUD statusline | - | `/oh-my-claudecode:hud` | +| `doctor` | Diagnose installation issues | - | `/oh-my-claudecode:doctor` | +| `help` | Show OMC usage guide | - | `/oh-my-claudecode:help` | +| `omc-setup` | One-time setup wizard | - | `/oh-my-claudecode:omc-setup` | +| `omc-default` | Configure local project | - | (internal) | +| `omc-default-global` | Configure global settings | - | (internal) | +| `ralph-init` | Initialize PRD for structured ralph | - | `/oh-my-claudecode:ralph-init` | +| `release` | Automated release workflow | - | `/oh-my-claudecode:release` | +| `cancel-autopilot` | Cancel active autopilot session | "stop autopilot", "cancel autopilot" | `/oh-my-claudecode:cancel-autopilot` | +| `cancel-ralph` | Cancel active ralph loop | "stop" in ralph | `/oh-my-claudecode:cancel-ralph` | +| `cancel-ultrawork` | Cancel ultrawork mode | "stop" in ultrawork | `/oh-my-claudecode:cancel-ultrawork` | +| `cancel-ultraqa` | Cancel ultraqa workflow | "stop" in ultraqa | `/oh-my-claudecode:cancel-ultraqa` | +| `research` | Parallel scientist orchestration | "research", "analyze data" | `/oh-my-claudecode:research` | + +### All 28 Agents + +Always use `oh-my-claudecode:` prefix when calling via Task tool. + +| Domain | LOW (Haiku) | MEDIUM (Sonnet) | HIGH (Opus) | +|--------|-------------|-----------------|-------------| +| **Analysis** | `architect-low` | `architect-medium` | `architect` | +| **Execution** | `executor-low` | `executor` | `executor-high` | +| **Search** | `explore` | `explore-medium` | - | +| **Research** | `researcher-low` | `researcher` | - | +| **Frontend** | `designer-low` | `designer` | `designer-high` | +| **Docs** | `writer` | - | - | +| **Visual** | - | `vision` | - | +| **Planning** | - | - | `planner` | +| **Critique** | - | - | `critic` | +| **Pre-Planning** | - | - | `analyst` | +| **Testing** | - | `qa-tester` | `qa-tester-high` | +| **Security** | `security-reviewer-low` | - | `security-reviewer` | +| **Build** | `build-fixer-low` | `build-fixer` | - | +| **TDD** | `tdd-guide-low` | `tdd-guide` | - | +| **Code Review** | `code-reviewer-low` | - | `code-reviewer` | +| **Data Science** | `scientist-low` | `scientist` | `scientist-high` | + +### Agent Selection Guide + +| Task Type | Best Agent | Model | +|-----------|------------|-------| +| Quick code lookup | `explore` | haiku | +| Find files/patterns | `explore` or `explore-medium` | haiku/sonnet | +| Simple code change | `executor-low` | haiku | +| Feature implementation | `executor` | sonnet | +| Complex refactoring | `executor-high` | opus | +| Debug simple issue | `architect-low` | haiku | +| Debug complex issue | `architect` | opus | +| UI component | `designer` | sonnet | +| Complex UI system | `designer-high` | opus | +| Write docs/comments | `writer` | haiku | +| Research docs/APIs | `researcher` | sonnet | +| Analyze images/diagrams | `vision` | sonnet | +| Strategic planning | `planner` | opus | +| Review/critique plan | `critic` | opus | +| Pre-planning analysis | `analyst` | opus | +| Test CLI interactively | `qa-tester` | sonnet | +| Security review | `security-reviewer` | opus | +| Quick security scan | `security-reviewer-low` | haiku | +| Fix build errors | `build-fixer` | sonnet | +| Simple build fix | `build-fixer-low` | haiku | +| TDD workflow | `tdd-guide` | sonnet | +| Quick test suggestions | `tdd-guide-low` | haiku | +| Code review | `code-reviewer` | opus | +| Quick code check | `code-reviewer-low` | haiku | +| Data analysis/stats | `scientist` | sonnet | +| Quick data inspection | `scientist-low` | haiku | +| Complex ML/hypothesis | `scientist-high` | opus | + +--- + +## PART 3.5: NEW FEATURES (v3.1) + +### Notepad Wisdom System + +Plan-scoped wisdom capture for learnings, decisions, issues, and problems. + +**Location:** `.omc/notepads/{plan-name}/` + +| File | Purpose | +|------|---------| +| `learnings.md` | Technical discoveries and patterns | +| `decisions.md` | Architectural and design decisions | +| `issues.md` | Known issues and workarounds | +| `problems.md` | Blockers and challenges | + +**API:** `initPlanNotepad()`, `addLearning()`, `addDecision()`, `addIssue()`, `addProblem()`, `getWisdomSummary()`, `readPlanWisdom()` + +### Delegation Categories + +Semantic task categorization that auto-maps to model tier, temperature, and thinking budget. + +| Category | Tier | Temperature | Thinking | Use For | +|----------|------|-------------|----------|---------| +| `visual-engineering` | HIGH | 0.7 | high | UI/UX, frontend, design systems | +| `ultrabrain` | HIGH | 0.3 | max | Complex reasoning, architecture, deep debugging | +| `artistry` | MEDIUM | 0.9 | medium | Creative solutions, brainstorming | +| `quick` | LOW | 0.1 | low | Simple lookups, basic operations | +| `writing` | MEDIUM | 0.5 | medium | Documentation, technical writing | + +**Auto-detection:** Categories detect from prompt keywords automatically. + +### Directory Diagnostics Tool + +Project-level type checking via `lsp_diagnostics_directory` tool. + +**Strategies:** +- `auto` (default) - Auto-selects best strategy, prefers tsc when tsconfig.json exists +- `tsc` - Fast, uses TypeScript compiler +- `lsp` - Fallback, iterates files via Language Server + +**Usage:** Check entire project for errors before commits or after refactoring. + +### Session Resume + +Background agents can be resumed with full context via `resume-session` tool. + +--- + +## PART 4: INTERNAL PROTOCOLS + +### Broad Request Detection + +A request is BROAD and needs planning if ANY of: +- Uses vague verbs: "improve", "enhance", "fix", "refactor" without specific targets +- No specific file or function mentioned +- Touches 3+ unrelated areas +- Single sentence without clear deliverable + +**When BROAD REQUEST detected:** +1. Invoke `explore` agent to understand codebase +2. Optionally invoke `architect` for guidance +3. THEN invoke `planner` skill with gathered context +4. Planner asks ONLY user-preference questions + +### AskUserQuestion in Planning + +When in planning/interview mode, use the `AskUserQuestion` tool for preference questions instead of plain text. This provides a clickable UI for faster user responses. + +**Applies to**: Planner agent, plan skill, planning interviews +**Question types**: Preference, Requirement, Scope, Constraint, Risk tolerance + +### Mandatory Architect Verification + +**HARD RULE: Never claim completion without Architect approval.** + +``` +1. Complete all work +2. Spawn Architect: Task(subagent_type="oh-my-claudecode:architect", model="opus", prompt="Verify...") +3. WAIT for response +4. If APPROVED → output completion +5. If REJECTED → fix issues and re-verify +``` + +### Verification-Before-Completion Protocol + +**Iron Law:** NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE + +Before ANY agent says "done", "fixed", or "complete": + +| Step | Action | +|------|--------| +| 1 | IDENTIFY: What command proves this claim? | +| 2 | RUN: Execute verification command | +| 3 | READ: Check output - did it pass? | +| 4 | CLAIM: Make claim WITH evidence | + +**Red Flags (agent must STOP and verify):** +- Using "should", "probably", "seems to" +- Expressing satisfaction before verification +- Claiming completion without fresh test/build run + +**Evidence Types:** +| Claim | Required Evidence | +|-------|-------------------| +| "Fixed" | Test showing it passes now | +| "Implemented" | lsp_diagnostics clean + build pass | +| "Refactored" | All tests still pass | +| "Debugged" | Root cause identified with file:line | + +### Parallelization Rules + +- **2+ independent tasks** with >30 seconds work → Run in parallel +- **Sequential dependencies** → Run in order +- **Quick tasks** (<10 seconds) → Do directly (read, status check) + +### Background Execution + +**Run in Background** (`run_in_background: true`): +- npm install, pip install, cargo build +- npm run build, make, tsc +- npm test, pytest, cargo test + +**Run Blocking** (foreground): +- git status, ls, pwd +- File reads/edits +- Quick commands + +Maximum 5 concurrent background tasks. + +### Context Persistence + +Use `` tags to survive conversation compaction: + +| Tag | Lifetime | Use For | +|-----|----------|---------| +| `info` | 7 days | Session-specific context | +| `info` | Permanent | Critical patterns/facts | + +**DO capture:** Architecture decisions, error resolutions, user preferences +**DON'T capture:** Progress (use todos), temporary state, info in AGENTS.md + +### Continuation Enforcement + +You are BOUND to your task list. Do not stop until EVERY task is COMPLETE. + +Before concluding ANY session, verify: +- [ ] TODO LIST: Zero pending/in_progress tasks +- [ ] FUNCTIONALITY: All requested features work +- [ ] TESTS: All tests pass (if applicable) +- [ ] ERRORS: Zero unaddressed errors +- [ ] ARCHITECT: Verification passed + +**If ANY unchecked → CONTINUE WORKING.** + +--- + +## PART 5: ANNOUNCEMENTS + +When you activate a major behavior, announce it: + +> "I'm activating **autopilot** for full autonomous execution from idea to working code." + +> "I'm activating **ralph-loop** to ensure this task completes fully." + +> "I'm activating **ultrawork** for maximum parallel execution." + +> "I'm starting a **planning session** - I'll interview you about requirements." + +> "I'm delegating this to the **architect** agent for deep analysis." + +This keeps users informed without requiring them to request features. + +--- + +## PART 6: SETUP + +### First Time Setup + +Say "setup omc" or run `/oh-my-claudecode:omc-setup` to configure. After that, everything is automatic. + +### Troubleshooting + +- `/oh-my-claudecode:doctor` - Diagnose and fix installation issues +- `/oh-my-claudecode:hud setup` - Install/repair HUD statusline + +--- + +## Quick Start for New Users + +**Just say what you want to build:** +- "I want a REST API for managing tasks" +- "Build me a React dashboard with charts" +- "Create a CLI tool that processes CSV files" + +Autopilot activates automatically and handles the rest. No commands needed. + +--- + +## Migration from 2.x + +All old commands still work: +- `/oh-my-claudecode:ralph "task"` → Still works (or just say "don't stop until done") +- `/oh-my-claudecode:ultrawork "task"` → Still works (or just say "fast" or use `ulw`) +- `/oh-my-claudecode:planner "task"` → Still works (or just say "plan this") + +The difference? You don't NEED them anymore. Everything auto-activates. + +**New in 3.x:** Autopilot mode provides the ultimate hands-off experience. diff --git a/src/main/java/com/yolo/keyborad/config/ElevenLabsProperties.java b/src/main/java/com/yolo/keyborad/config/ElevenLabsProperties.java new file mode 100644 index 0000000..e0fc266 --- /dev/null +++ b/src/main/java/com/yolo/keyborad/config/ElevenLabsProperties.java @@ -0,0 +1,66 @@ +package com.yolo.keyborad.config; + +import lombok.Data; +import org.springframework.boot.context.properties.ConfigurationProperties; +import org.springframework.stereotype.Component; + +/** + * ElevenLabs TTS 配置 + * + * @author ziin + */ +@Data +@Component +@ConfigurationProperties(prefix = "elevenlabs") +public class ElevenLabsProperties { + + /** + * API Key + */ + private String apiKey; + + /** + * 基础 URL + */ + private String baseUrl = "https://api.elevenlabs.io/v1"; + + /** + * 默认语音 ID + */ + private String voiceId; + + /** + * 模型 ID + */ + private String modelId = "eleven_multilingual_v2"; + + /** + * 输出格式 + */ + private String outputFormat = "mp3_44100_128"; + + /** + * 稳定性 (0-1) + */ + private Double stability = 0.5; + + /** + * 相似度增强 (0-1) + */ + private Double similarityBoost = 0.75; + + /** + * 风格 (0-1) + */ + private Double style = 0.0; + + /** + * 语速 (0.7-1.2) + */ + private Double speed = 1.0; + + /** + * 使用说话人增强 + */ + private Boolean useSpeakerBoost = true; +} diff --git a/src/main/java/com/yolo/keyborad/config/SaTokenConfigure.java b/src/main/java/com/yolo/keyborad/config/SaTokenConfigure.java index 0a61750..68bf69c 100644 --- a/src/main/java/com/yolo/keyborad/config/SaTokenConfigure.java +++ b/src/main/java/com/yolo/keyborad/config/SaTokenConfigure.java @@ -109,7 +109,9 @@ public class SaTokenConfigure implements WebMvcConfigurer { "/themes/listAllStyles", "/wallet/transactions", "/themes/restore", - "/chat/message" + "/chat/message", + "/chat/voice", + "/chat/audio/*" }; } @Bean diff --git a/src/main/java/com/yolo/keyborad/controller/ChatController.java b/src/main/java/com/yolo/keyborad/controller/ChatController.java index 2ffe6c7..5a25ec6 100644 --- a/src/main/java/com/yolo/keyborad/controller/ChatController.java +++ b/src/main/java/com/yolo/keyborad/controller/ChatController.java @@ -11,6 +11,9 @@ import com.yolo.keyborad.mapper.QdrantPayloadMapper; import com.yolo.keyborad.model.dto.chat.ChatReq; import com.yolo.keyborad.model.dto.chat.ChatSaveReq; import com.yolo.keyborad.model.dto.chat.ChatStreamMessage; +import com.yolo.keyborad.model.vo.AudioTaskVO; +import com.yolo.keyborad.model.vo.ChatMessageVO; +import com.yolo.keyborad.model.vo.ChatVoiceVO; import com.yolo.keyborad.service.ChatService; import com.yolo.keyborad.service.impl.QdrantVectorService; import io.qdrant.client.grpc.JsonWithInt; @@ -46,19 +49,30 @@ public class ChatController { @PostMapping("/message") - @Operation(summary = "同步对话", description = "发送消息给大模型，同步返回回复") - public BaseResponse message(@RequestParam("content") String content) { + @Operation(summary = "同步对话", description = "发送消息给大模型，同步返回 AI 响应，异步生成音频") + public BaseResponse message(@RequestParam("content") String content) { if (StrUtil.isBlank(content)) { throw new BusinessException(ErrorCode.PARAMS_ERROR, "消息内容不能为空"); } String userId = StpUtil.getLoginIdAsString(); - String response = chatService.message(content, userId); + ChatMessageVO result = chatService.message(content, userId); - return ResultUtils.success(response); + return ResultUtils.success(result); } + @GetMapping("/audio/{audioId}") + @Operation(summary = "查询音频状态", description = "根据音频 ID 查询音频生成状态和 URL") + public BaseResponse getAudioTask(@PathVariable("audioId") String audioId) { + if (StrUtil.isBlank(audioId)) { + throw new BusinessException(ErrorCode.PARAMS_ERROR, "音频 ID 不能为空"); + } + + AudioTaskVO result = chatService.getAudioTask(audioId); + return ResultUtils.success(result); + } + @PostMapping("/talk") @Operation(summary = "聊天润色接口", description = "聊天润色接口") public Flux> talk(@RequestBody ChatReq chatReq){ diff --git a/src/main/java/com/yolo/keyborad/model/vo/AudioTaskVO.java b/src/main/java/com/yolo/keyborad/model/vo/AudioTaskVO.java new file mode 100644 index 0000000..de87b40 --- /dev/null +++ b/src/main/java/com/yolo/keyborad/model/vo/AudioTaskVO.java @@ -0,0 +1,37 @@ +package com.yolo.keyborad.model.vo; + +import io.swagger.v3.oas.annotations.media.Schema; +import lombok.AllArgsConstructor; +import lombok.Builder; +import lombok.Data; +import lombok.NoArgsConstructor; + +/** + * 音频任务状态 + * + * @author ziin + */ +@Data +@Builder +@NoArgsConstructor +@AllArgsConstructor +@Schema(description = "音频任务状态") +public class AudioTaskVO { + + @Schema(description = "音频任务 ID") + private String audioId; + + @Schema(description = "任务状态: pending/processing/completed/failed") + private String status; + + @Schema(description = "音频 URL (completed 时返回)") + private String audioUrl; + + @Schema(description = "错误信息 (failed 时返回)") + private String errorMessage; + + public static final String STATUS_PENDING = "pending"; + public static final String STATUS_PROCESSING = "processing"; + public static final String STATUS_COMPLETED = "completed"; + public static final String STATUS_FAILED = "failed"; +} diff --git a/src/main/java/com/yolo/keyborad/model/vo/ChatMessageVO.java b/src/main/java/com/yolo/keyborad/model/vo/ChatMessageVO.java new file mode 100644 index 0000000..f10734b --- /dev/null +++ b/src/main/java/com/yolo/keyborad/model/vo/ChatMessageVO.java @@ -0,0 +1,29 @@ +package com.yolo.keyborad.model.vo; + +import io.swagger.v3.oas.annotations.media.Schema; +import lombok.AllArgsConstructor; +import lombok.Builder; +import lombok.Data; +import lombok.NoArgsConstructor; + +/** + * 消息响应（含异步音频） + * + * @author ziin + */ +@Data +@Builder +@NoArgsConstructor +@AllArgsConstructor +@Schema(description = "消息响应") +public class ChatMessageVO { + + @Schema(description = "AI 响应文本") + private String aiResponse; + + @Schema(description = "音频任务 ID，用于查询音频状态") + private String audioId; + + @Schema(description = "LLM 耗时（毫秒）") + private Long llmDuration; +} diff --git a/src/main/java/com/yolo/keyborad/model/vo/ChatVoiceVO.java b/src/main/java/com/yolo/keyborad/model/vo/ChatVoiceVO.java new file mode 100644 index 0000000..dd71944 --- /dev/null +++ b/src/main/java/com/yolo/keyborad/model/vo/ChatVoiceVO.java @@ -0,0 +1,32 @@ +package com.yolo.keyborad.model.vo; + +import io.swagger.v3.oas.annotations.media.Schema; +import lombok.AllArgsConstructor; +import lombok.Builder; +import lombok.Data; +import lombok.NoArgsConstructor; + +/** + * 语音对话响应 + * + * @author ziin + */ +@Data +@Builder +@NoArgsConstructor +@AllArgsConstructor +@Schema(description = "语音对话响应") +public class ChatVoiceVO { + + @Schema(description = "用户输入内容") + private String content; + + @Schema(description = "AI 响应文本") + private String aiResponse; + + @Schema(description = "AI 语音音频 URL (R2)") + private String audioUrl; + + @Schema(description = "处理耗时（毫秒）") + private Long duration; +} diff --git a/src/main/java/com/yolo/keyborad/model/vo/TextToSpeechVO.java b/src/main/java/com/yolo/keyborad/model/vo/TextToSpeechVO.java new file mode 100644 index 0000000..b77dbca --- /dev/null +++ b/src/main/java/com/yolo/keyborad/model/vo/TextToSpeechVO.java @@ -0,0 +1,26 @@ +package com.yolo.keyborad.model.vo; + +import io.swagger.v3.oas.annotations.media.Schema; +import lombok.AllArgsConstructor; +import lombok.Builder; +import lombok.Data; +import lombok.NoArgsConstructor; + +/** + * TTS 语音合成结果 + * + * @author ziin + */ +@Data +@Builder +@NoArgsConstructor +@AllArgsConstructor +@Schema(description = "TTS 语音合成结果") +public class TextToSpeechVO { + + @Schema(description = "音频 Base64") + private String audioBase64; + + @Schema(description = "音频 URL (R2)") + private String audioUrl; +} diff --git a/src/main/java/com/yolo/keyborad/service/ChatService.java b/src/main/java/com/yolo/keyborad/service/ChatService.java index fb2cd8d..5df965d 100644 --- a/src/main/java/com/yolo/keyborad/service/ChatService.java +++ b/src/main/java/com/yolo/keyborad/service/ChatService.java @@ -2,6 +2,9 @@ package com.yolo.keyborad.service; import com.yolo.keyborad.model.dto.chat.ChatReq; import com.yolo.keyborad.model.dto.chat.ChatStreamMessage; +import com.yolo.keyborad.model.vo.AudioTaskVO; +import com.yolo.keyborad.model.vo.ChatMessageVO; +import com.yolo.keyborad.model.vo.ChatVoiceVO; import org.springframework.http.codec.ServerSentEvent; import reactor.core.publisher.Flux; @@ -13,11 +16,20 @@ public interface ChatService { Flux> talk(ChatReq chatReq); /** - * 同步对话 + * 同步对话（异步生成音频） * * @param content 用户消息内容 * @param userId 用户ID - * @return AI 响应 + * @return AI 响应 + 音频任务 ID */ - String message(String content, String userId); + ChatMessageVO message(String content, String userId); + + /** + * 查询音频任务状态 + * + * @param audioId 音频任务 ID + * @return 音频任务状态 + */ + AudioTaskVO getAudioTask(String audioId); + } diff --git a/src/main/java/com/yolo/keyborad/service/ElevenLabsService.java b/src/main/java/com/yolo/keyborad/service/ElevenLabsService.java new file mode 100644 index 0000000..bb60e96 --- /dev/null +++ b/src/main/java/com/yolo/keyborad/service/ElevenLabsService.java @@ -0,0 +1,28 @@ +package com.yolo.keyborad.service; + +import com.yolo.keyborad.model.vo.TextToSpeechVO; + +/** + * ElevenLabs TTS 语音合成服务接口 + * + * @author ziin + */ +public interface ElevenLabsService { + + /** + * 将文本转换为语音（带时间戳） + * + * @param text 要转换的文本 + * @return 语音合成结果，包含 base64 音频 + */ + TextToSpeechVO textToSpeechWithTimestamps(String text); + + /** + * 将文本转换为语音（带时间戳），使用指定语音 + * + * @param text 要转换的文本 + * @param voiceId 语音 ID + * @return 语音合成结果 + */ + TextToSpeechVO textToSpeechWithTimestamps(String text, String voiceId); +} diff --git a/src/main/java/com/yolo/keyborad/service/impl/ChatServiceImpl.java b/src/main/java/com/yolo/keyborad/service/impl/ChatServiceImpl.java index d95f9d5..002249b 100644 --- a/src/main/java/com/yolo/keyborad/service/impl/ChatServiceImpl.java +++ b/src/main/java/com/yolo/keyborad/service/impl/ChatServiceImpl.java @@ -14,21 +14,34 @@ import com.yolo.keyborad.model.entity.KeyboardCharacter; import com.yolo.keyborad.model.entity.KeyboardUser; import com.yolo.keyborad.model.entity.KeyboardUserCallLog; import com.yolo.keyborad.model.entity.KeyboardUserQuotaTotal; +import com.yolo.keyborad.model.vo.AudioTaskVO; +import com.yolo.keyborad.model.vo.ChatMessageVO; +import com.yolo.keyborad.model.vo.ChatVoiceVO; +import com.yolo.keyborad.model.vo.TextToSpeechVO; import com.yolo.keyborad.service.*; import jakarta.annotation.Resource; import lombok.extern.slf4j.Slf4j; +import org.dromara.x.file.storage.core.FileInfo; +import org.dromara.x.file.storage.core.FileStorageService; import org.springframework.ai.chat.client.ChatClient; import org.springframework.ai.openai.OpenAiChatOptions; +import org.springframework.data.redis.core.StringRedisTemplate; import org.springframework.http.codec.ServerSentEvent; +import org.springframework.scheduling.annotation.Async; import org.springframework.stereotype.Service; import reactor.core.publisher.Flux; import reactor.core.publisher.Mono; import reactor.core.scheduler.Schedulers; import java.math.BigDecimal; +import java.io.ByteArrayInputStream; import java.util.ArrayList; +import java.util.Base64; import java.util.Date; import java.util.List; +import java.util.UUID; +import java.util.concurrent.CompletableFuture; +import java.util.concurrent.TimeUnit; import java.util.concurrent.atomic.AtomicInteger; import java.util.concurrent.atomic.AtomicReference; @@ -61,6 +74,18 @@ public class ChatServiceImpl implements ChatService { @Resource private UserService userService; + @Resource + private ElevenLabsService elevenLabsService; + + @Resource + private FileStorageService fileStorageService; + + @Resource + private StringRedisTemplate stringRedisTemplate; + + private static final String AUDIO_TASK_PREFIX = "audio:task:"; + private static final long AUDIO_TASK_EXPIRE_SECONDS = 3600; // 1小时过期 + private final NacosAppConfigCenter.DynamicAppConfig cfgHolder; public ChatServiceImpl(NacosAppConfigCenter.DynamicAppConfig cfgHolder) { @@ -323,18 +348,43 @@ public class ChatServiceImpl implements ChatService { } /** - * 同步对话 + * 同步对话（异步生成音频） * * @param content 用户消息内容 * @param userId 用户ID - * @return AI 响应 + * @return AI 响应 + 音频任务 ID */ @Override - public String message(String content, String userId) { + public ChatMessageVO message(String content, String userId) { log.info("同步对话请求, userId: {}, content: {}", userId, content); long startTime = System.currentTimeMillis(); + String response = callLLM(content); + + long llmDuration = System.currentTimeMillis() - startTime; + log.info("LLM 完成, userId: {}, 耗时: {}ms, 响应长度: {}", userId, llmDuration, response.length()); + + // 生成音频任务 ID + String audioId = UUID.randomUUID().toString().replace("-", ""); + + // 初始化音频任务状态为 processing + setAudioTaskStatus(audioId, AudioTaskVO.STATUS_PROCESSING, null, null); + + // 异步执行 TTS + R2 上传 + CompletableFuture.runAsync(() -> processAudioAsync(audioId, response, userId)); + + return ChatMessageVO.builder() + .aiResponse(response) + .audioId(audioId) + .llmDuration(llmDuration) + .build(); + } + + /** + * 调用 LLM 生成响应 + */ + private String callLLM(String content) { String systemPrompt = """ ROLE: You are "Tiffany", a 17-year-old popular high school student from Beverly Hills. You are sassy, judgmental, impatient, but secretly caring. @@ -347,16 +397,103 @@ public class ChatServiceImpl implements ChatService { Keep responses concise (2-3 sentences max) for real-time conversation. """; - String response = client + return client .prompt() .system(systemPrompt) .user(content) .call() .content(); + } - long duration = System.currentTimeMillis() - startTime; - log.info("同步对话完成, userId: {}, 耗时: {}ms, 响应长度: {}", userId, duration, response.length()); + /** + * 异步处理音频：TTS 转换 + 上传 R2 + */ + private void processAudioAsync(String audioId, String text, String userId) { + try { + log.info("开始异步音频处理, audioId: {}", audioId); + long startTime = System.currentTimeMillis(); - return response; + // 1. TTS 转换 + long ttsStart = System.currentTimeMillis(); + TextToSpeechVO ttsResult = elevenLabsService.textToSpeechWithTimestamps(text); + long ttsDuration = System.currentTimeMillis() - ttsStart; + log.info("TTS 完成, audioId: {}, 耗时: {}ms", audioId, ttsDuration); + + // 2. 上传到 R2 + long uploadStart = System.currentTimeMillis(); + String audioUrl = uploadAudioToR2(ttsResult.getAudioBase64(), userId); + long uploadDuration = System.currentTimeMillis() - uploadStart; + log.info("R2 上传完成, audioId: {}, 耗时: {}ms, URL: {}", audioId, uploadDuration, audioUrl); + + // 3. 更新任务状态为完成 + setAudioTaskStatus(audioId, AudioTaskVO.STATUS_COMPLETED, audioUrl, null); + + long totalDuration = System.currentTimeMillis() - startTime; + log.info("异步音频处理完成, audioId: {}, 总耗时: {}ms (TTS: {}ms, Upload: {}ms)", + audioId, totalDuration, ttsDuration, uploadDuration); + + } catch (Exception e) { + log.error("异步音频处理失败, audioId: {}", audioId, e); + setAudioTaskStatus(audioId, AudioTaskVO.STATUS_FAILED, null, e.getMessage()); + } + } + + /** + * 设置音频任务状态 + */ + private void setAudioTaskStatus(String audioId, String status, String audioUrl, String errorMessage) { + String key = AUDIO_TASK_PREFIX + audioId; + String value = status + "|" + (audioUrl != null ? audioUrl : "") + "|" + (errorMessage != null ? errorMessage : ""); + stringRedisTemplate.opsForValue().set(key, value, AUDIO_TASK_EXPIRE_SECONDS, TimeUnit.SECONDS); + } + + /** + * 查询音频任务状态 + */ + @Override + public AudioTaskVO getAudioTask(String audioId) { + String key = AUDIO_TASK_PREFIX + audioId; + String value = stringRedisTemplate.opsForValue().get(key); + + if (cn.hutool.core.util.StrUtil.isBlank(value)) { + return AudioTaskVO.builder() + .audioId(audioId) + .status(AudioTaskVO.STATUS_PENDING) + .build(); + } + + String[] parts = value.split("\\|", -1); + return AudioTaskVO.builder() + .audioId(audioId) + .status(parts[0]) + .audioUrl(parts.length > 1 && !parts[1].isEmpty() ? parts[1] : null) + .errorMessage(parts.length > 2 && !parts[2].isEmpty() ? parts[2] : null) + .build(); + } + + + /** + * 上传音频到 R2 + */ + private String uploadAudioToR2(String audioBase64, String userId) { + if (cn.hutool.core.util.StrUtil.isBlank(audioBase64)) { + throw new BusinessException(ErrorCode.SYSTEM_ERROR, "音频数据为空"); + } + + byte[] audioBytes = Base64.getDecoder().decode(audioBase64); + String fileName = UUID.randomUUID() + ".mp3"; + + FileInfo fileInfo = fileStorageService.of(new ByteArrayInputStream(audioBytes)) + .setPath(userId + "/") + .setPlatform("cloudflare-r2") + .setSaveFilename(fileName) + .setOriginalFilename(fileName) + .upload(); + + if (fileInfo == null || cn.hutool.core.util.StrUtil.isBlank(fileInfo.getUrl())) { + throw new BusinessException(ErrorCode.SYSTEM_ERROR, "音频上传失败"); + } + + return fileInfo.getUrl(); } } diff --git a/src/main/java/com/yolo/keyborad/service/impl/ElevenLabsServiceImpl.java b/src/main/java/com/yolo/keyborad/service/impl/ElevenLabsServiceImpl.java new file mode 100644 index 0000000..d21ed23 --- /dev/null +++ b/src/main/java/com/yolo/keyborad/service/impl/ElevenLabsServiceImpl.java @@ -0,0 +1,175 @@ +package com.yolo.keyborad.service.impl; + +import cn.hutool.core.util.StrUtil; +import com.alibaba.fastjson.JSON; +import com.alibaba.fastjson.JSONObject; +import com.yolo.keyborad.common.ErrorCode; +import com.yolo.keyborad.config.ElevenLabsProperties; +import com.yolo.keyborad.exception.BusinessException; +import com.yolo.keyborad.model.vo.TextToSpeechVO; +import com.yolo.keyborad.service.ElevenLabsService; +import jakarta.annotation.Resource; +import lombok.extern.slf4j.Slf4j; +import org.springframework.stereotype.Service; + +import java.io.ByteArrayOutputStream; +import java.io.InputStream; +import java.io.OutputStream; +import java.net.HttpURLConnection; +import java.net.URL; +import java.nio.charset.StandardCharsets; +import java.util.HashMap; +import java.util.Map; + +/** + * ElevenLabs TTS 语音合成服务实现 + * 参考: https://elevenlabs.io/docs/api-reference/text-to-speech/convert-with-timestamps + * + * @author ziin + */ +@Service +@Slf4j +public class ElevenLabsServiceImpl implements ElevenLabsService { + + @Resource + private ElevenLabsProperties elevenLabsProperties; + + private static final int MAX_TEXT_LENGTH = 5000; + + @Override + public TextToSpeechVO textToSpeechWithTimestamps(String text) { + return textToSpeechWithTimestamps(text, elevenLabsProperties.getVoiceId()); + } + + @Override + public TextToSpeechVO textToSpeechWithTimestamps(String text, String voiceId) { + // 1. 参数验证 + if (StrUtil.isBlank(text)) { + throw new BusinessException(ErrorCode.PARAMS_ERROR, "文本内容不能为空"); + } + + if (text.length() > MAX_TEXT_LENGTH) { + throw new BusinessException(ErrorCode.PARAMS_ERROR, + "文本长度超出限制，最大支持 " + MAX_TEXT_LENGTH + " 字符"); + } + + if (StrUtil.isBlank(voiceId)) { + voiceId = elevenLabsProperties.getVoiceId(); + } + + HttpURLConnection connection = null; + try { + // 2. 构建请求 URL + String requestUrl = buildRequestUrl(voiceId); + URL url = new URL(requestUrl); + + // 3. 创建连接 + connection = (HttpURLConnection) url.openConnection(); + connection.setRequestMethod("POST"); + connection.setDoOutput(true); + connection.setDoInput(true); + connection.setConnectTimeout(30000); + connection.setReadTimeout(60000); + + // 4. 设置请求头 + connection.setRequestProperty("Content-Type", "application/json"); + connection.setRequestProperty("xi-api-key", elevenLabsProperties.getApiKey()); + + // 5. 构建请求体 + Map requestBody = buildRequestBody(text); + String jsonBody = JSON.toJSONString(requestBody); + + log.info("调用 ElevenLabs TTS API, voiceId: {}, 文本长度: {}", voiceId, text.length()); + long startTime = System.currentTimeMillis(); + + // 6. 发送请求 + try (OutputStream os = connection.getOutputStream()) { + byte[] input = jsonBody.getBytes(StandardCharsets.UTF_8); + os.write(input, 0, input.length); + } + + // 7. 获取响应 + int responseCode = connection.getResponseCode(); + long duration = System.currentTimeMillis() - startTime; + log.info("ElevenLabs TTS API 响应码: {}, 耗时: {}ms", responseCode, duration); + + if (responseCode == HttpURLConnection.HTTP_OK) { + // 读取响应 JSON + try (InputStream is = connection.getInputStream(); + ByteArrayOutputStream baos = new ByteArrayOutputStream()) { + byte[] buffer = new byte[8192]; + int bytesRead; + while ((bytesRead = is.read(buffer)) != -1) { + baos.write(buffer, 0, bytesRead); + } + String responseJson = baos.toString(StandardCharsets.UTF_8); + JSONObject jsonResponse = JSON.parseObject(responseJson); + + String audioBase64 = jsonResponse.getString("audio_base64"); + + log.info("语音合成成功，Base64长度: {}", audioBase64.length()); + + return TextToSpeechVO.builder() + .audioBase64(audioBase64) + .build(); + } + } else { + // 读取错误信息 + String errorMsg = ""; + try (InputStream es = connection.getErrorStream()) { + if (es != null) { + ByteArrayOutputStream baos = new ByteArrayOutputStream(); + byte[] buffer = new byte[1024]; + int bytesRead; + while ((bytesRead = es.read(buffer)) != -1) { + baos.write(buffer, 0, bytesRead); + } + errorMsg = baos.toString(StandardCharsets.UTF_8); + } + } + log.error("ElevenLabs TTS API 调用失败, 状态码: {}, 错误信息: {}", responseCode, errorMsg); + throw new BusinessException(ErrorCode.SYSTEM_ERROR, "语音合成服务异常: " + responseCode); + } + + } catch (BusinessException e) { + throw e; + } catch (Exception e) { + log.error("调用 ElevenLabs TTS API 发生异常", e); + throw new BusinessException(ErrorCode.SYSTEM_ERROR, "语音合成服务异常: " + e.getMessage()); + } finally { + if (connection != null) { + connection.disconnect(); + } + } + } + + /** + * 构建 ElevenLabs TTS API 请求 URL（带时间戳） + */ + private String buildRequestUrl(String voiceId) { + StringBuilder url = new StringBuilder(elevenLabsProperties.getBaseUrl()); + url.append("/text-to-speech/").append(voiceId).append("/with-timestamps"); + url.append("?output_format=").append(elevenLabsProperties.getOutputFormat()); + return url.toString(); + } + + /** + * 构建请求体 + */ + private Map buildRequestBody(String text) { + Map requestBody = new HashMap<>(); + requestBody.put("text", text); + requestBody.put("model_id", elevenLabsProperties.getModelId()); + + // 设置语音参数 + Map voiceSettings = new HashMap<>(); + voiceSettings.put("stability", elevenLabsProperties.getStability()); + voiceSettings.put("similarity_boost", elevenLabsProperties.getSimilarityBoost()); + voiceSettings.put("style", elevenLabsProperties.getStyle()); + voiceSettings.put("speed", elevenLabsProperties.getSpeed()); + voiceSettings.put("use_speaker_boost", elevenLabsProperties.getUseSpeakerBoost()); + requestBody.put("voice_settings", voiceSettings); + + return requestBody; + } +} diff --git a/src/main/resources/application-dev.yml b/src/main/resources/application-dev.yml index 730aa3d..9174723 100644 --- a/src/main/resources/application-dev.yml +++ b/src/main/resources/application-dev.yml @@ -70,13 +70,13 @@ dromara: base-path: avatar/ # 基础路径 - platform: cloudflare-r2-apac # 存储平台标识 enable-storage: true # 启用存储 - access-key: 550b33cc4d53e05c2e438601f8a0e209 - secret-key: df4d529cdae44e6f614ca04f4dc0f1f9a299e57367181243e8abdc7f7c28e99a + access-key: eda135fe4fda649acecfa4bb49b0c30c + secret-key: ee557acaccf44caef985b5cac89db311a0923c72c9f4b8c5f32089c6ebb47a79 region: APAC # 区域 end-point: https://b632a61caa85401f63c9b32eef3a74c8.r2.cloudflarestorage.com/keyboardtest # 端点 bucket-name: keyboardtest #桶名称 domain: https://cdn.loveamorkey.com/ # 访问域名，注意末尾的'/'，例如：https://abcd.s3.ap-east-1.amazonaws.com/ - base-path: / # 基础路径 + base-path: tts/ # 基础路径 ############## Sa-Token 配置 (参考文档: https://sa-token.cc) ############## sa-token: @@ -99,4 +99,10 @@ nacos: config: server-addr: 127.0.0.1:8848 group: DEFAULT_GROUP - data-id: keyboard_default-config.yaml \ No newline at end of file + data-id: keyboard_default-config.yaml + +elevenlabs: + api-key: sk_25339d32bb14c91f460ed9fce83a1951672f07846a7a10ce + voice-id: JBFqnCBsd6RMkjVDRZzb + model-id: eleven_turbo_v2_5 + output-format: mp3_44100_128 \ No newline at end of file diff --git a/src/main/resources/application.yml b/src/main/resources/application.yml index 05499ca..f50851c 100644 --- a/src/main/resources/application.yml +++ b/src/main/resources/application.yml @@ -1,13 +1,13 @@ spring: ai: openai: -# api-key: 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 - api-key: sk-cf112f49cf4d4138a49575cda1f852b4 -# base-url: https://gateway.ai.cloudflare.com/v1/b632a61caa85401f63c9b32eef3a74c8/aigetway/openrouter - base-url: https://dashscope-intl.aliyuncs.com/compatible-mode/ + api-key: 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 +# api-key: sk-cf112f49cf4d4138a49575cda1f852b4 + base-url: https://gateway.ai.cloudflare.com/v1/b632a61caa85401f63c9b32eef3a74c8/aigetway/openrouter +# base-url: https://dashscope-intl.aliyuncs.com/compatible-mode/ chat: options: - model: qwen-plus + model: google/gemini-2.5-flash-lite embedding: options: model: text-embedding-v4