Commit Graph
47 Commits
Author SHA1 Message Date
Rogeeandrogee 1287b7702a fix(HH-600): isolate notification Redis lifecycle (#157)
Co-authored-by: Rogee <rogee@ipao.vip>
2026-08-24 12:24:34 +08:00
Rogeeandrogee e8c010406d fix(security): redact database query parameters (HH-596) (#159)
Co-authored-by: Rogee <rogee@ipao.vip>
2026-08-24 12:22:16 +08:00
Rogeeandrogee 57f8a64fd8 fix(HH-591): bound notification shutdown XACK (#154)
Co-authored-by: Rogee <rogee@ipao.vip>
2026-08-24 11:36:24 +08:00
Rogeeandrogee 2c6bee2b37 fix(HH-581): keep widget websocket on visitor auth (#152)
Co-authored-by: Rogee <rogee@ipao.vip>
2026-08-24 10:54:38 +08:00
Rogeeandrogee f36606a4f2 HH-564: harden durable realtime publish boundaries (#139)
* fix(HH-564): harden durable realtime enqueue

* fix(HH-564): wire production SSE stream

---------

Co-authored-by: Rogee <rogee@ipao.vip>
2026-08-23 23:38:00 +08:00
Rogeeandrogee 60a6ac4785 fix: restore web widget realtime replies (HH-556) (#136)
* fix: restore web widget realtime replies (HH-556)

* fix: make realtime delivery durable (HH-556)

* fix: make realtime message outbox atomic (HH-556)

---------

Co-authored-by: Rogee <rogee@ipao.vip>
2026-08-23 22:35:10 +08:00
Rogeeandrogee 17244bcc9d HH-554: connect auto-assignment runtime policy (#135)
* fix(HH-554): connect auto-assignment runtime policy

* fix(HH-554): bound and coalesce assignment jobs

* fix(HH-554): drain assignment backlog safely

* fix(HH-554): hold assignment claim through retries

---------

Co-authored-by: Rogee <rogee@ipao.vip>
2026-08-23 22:28:43 +08:00
Rogeeandrogee f719529d66 fix(security): harden auth and secret handling (HH-444) (#101)
* fix(security): harden auth and credential handling (HH-444)

* fix(security): address HH-444 review blockers

* fix(security): close remaining HH-444 review blockers

---------

Co-authored-by: Rogee <rogee@ipao.vip>
2026-08-22 15:45:06 +08:00
Rogeeandrogee 798ea43c2f HH-442: isolate runtime processes and harden shutdown (#90)
* HH-442: isolate runtime processes and harden shutdown

* HH-442: harden worker shutdown races

* HH-442: gate dependency shutdown on active handlers

---------

Co-authored-by: Rogee <rogee@ipao.vip>
2026-08-22 02:38:15 +08:00
Rogeeandrogee 6d6d80dd86 HH-441: harden durable storage and recovery (#92)
* HH-441: harden durable storage and recovery

* HH-441: clear recovery review blockers

* HH-441: enforce offsite backup failure domain

---------

Co-authored-by: Rogee <rogee@ipao.vip>
2026-08-22 02:16:02 +08:00
Rogeeandrogee 77c91662d2 HH-438: close upload and remote URL attack surfaces (#89)
* HH-438: close upload and remote URL attack surfaces

* HH-438: use valid PNG in direct upload test

* HH-438: align PostgreSQL upload staging schema

* HH-438: run upload migrations before PostgreSQL E2E

---------

Co-authored-by: Rogee <rogee@ipao.vip>
2026-08-21 20:36:52 +08:00
Rogeeandrogee 60ad320e8d [H-337] Fix Captain provider runtime and knowledge flow (#61)
* fix(H-337): configure Captain provider runtime

* fix(captain): make knowledge rebuild atomic

* fix(captain): scope retrieval provider failures

---------

Co-authored-by: Rogee <rogee@ipao.vip>
2026-08-20 14:46:01 +08:00
Rogeeandrogee 3d9817c9f5 H-337: fix Web Channel availability and realtime delivery (#60)
* H-337: fix Web Channel availability and realtime delivery

* fix(widget): preserve realtime sender and activity contracts

* fix(widget): keep realtime sender payloads consistent

* fix(widget): make public message persistence atomic

* fix(inbox): keep availability projection out of schema

---------

Co-authored-by: Rogee <rogee@ipao.vip>
2026-08-20 14:30:05 +08:00
Rogeeandrogee 6c78820a1f H-338: close H-335 release blockers (#59)
* H-16: align takeover with channel AI workflow (#2)

* feat(conversations): complete manual AI takeover

* fix(conversations): align AI takeover flow with channel AI

* fix(conversations): close takeover review gaps

---------

Co-authored-by: Rogee <rogee@ipao.vip>

* feat(shangwutong): sync customer names back to channel (#3)

Co-authored-by: Rogee <rogee@ipao.vip>

* fix(shangwutong): close contact sync review gaps (#4)

Co-authored-by: Rogee <rogee@ipao.vip>

* H-28: harden Shangwutong CID sync (#5)

* fix(shangwutong): close contact sync review gaps

* fix(shangwutong): harden CID sync boundaries

---------

Co-authored-by: Rogee <rogee@ipao.vip>

* fix(conversations): sync AI takeover exit in realtime (#6)

Co-authored-by: Rogee <rogee@ipao.vip>

* test(shangwutong): cover CID rename reliability (#7)

Co-authored-by: Rogee <rogee@ipao.vip>

* H-43: fix WEB Captain takeover E2E flow (#8)

* test(shangwutong): cover CID rename reliability

* H-43: fix WEB Captain takeover flow

* H-48: preserve compatible provider model

* H-49: make Captain takeover atomic

* H-50: prevent duplicate widget initialization

---------

Co-authored-by: Rogee <rogee@ipao.vip>

* H-55: make Captain bindings atomic (#9)

Co-authored-by: Rogee <rogee@ipao.vip>

* H-60: harden Captain migration rollback and concurrency

* chore(agent): baseline — uncommitted work from the local directory

* H-335: add safe Captain skills and user deactivation

* H-338: close auth and Captain review blockers

* H-338: close assignment and session races

* H-338: close assignment and websocket invalidation gaps

* H-338: enforce assignment write invariants

---------

Co-authored-by: Rogee <rogee@ipao.vip>
2026-08-20 10:21:19 +08:00
Rogeeandrogee 2b182f9956 H-300: wire Captain Skills into Web runtime (#48)
* H-300: wire Captain Skills into Web runtime

* H-300: enforce effective model and conservative skill budget

* H-300: fix CI gosec step

* ci: extend golangci-lint timeout

* fix lint findings across backend

* fix(push): resolve delivery protocol blockers

* test(repository): close SQLite test databases

* test(repository): reuse SQLite schema per package

* H-307: restore backend Go cache in CI

* H-307: prefetch modules before cold lint

* H-307: resolve govulncheck security gate

* H-307: build lint with patched Go toolchain

* H-307: clear remaining security scan findings

---------

Co-authored-by: Rogee <rogee@ipao.vip>
2026-08-19 07:08:14 +08:00
Rogeeandrogee 0f2b8d7857 H-289: add Captain Skill management API (#46)
* H-289: add Captain Skill management API

* H-289: guard Captain Skill updates with CAS

* H-289: version all Captain Skill updates

---------

Co-authored-by: Rogee <rogee@ipao.vip>
2026-08-18 14:29:10 +08:00
Rogeeandrogee 6a3cb49781 H-105: ground Captain replies with inbox knowledge (#18)
* H-105: ground Captain replies with inbox knowledge

* H-105: harden Captain grounding

* H-126: exclude deleted article embeddings

---------

Co-authored-by: Rogee <rogee@ipao.vip>
2026-08-14 19:41:45 +08:00
Rogeeandrogee 0e9bf8dc14 fix(shangwutong): close contact sync review gaps (#4)
Co-authored-by: Rogee <rogee@ipao.vip>
2026-08-13 01:21:07 +08:00
Rogeeandrogee 406e7a07fe feat(shangwutong): sync customer names back to channel (#3)
Co-authored-by: Rogee <rogee@ipao.vip>
2026-08-12 22:58:46 +08:00
rogee 4bf6ba6b20 feat(conversations): complete manual AI takeover 2026-08-12 21:16:49 +08:00
Rogee 4611c0201f test: improve backend unit coverage 2026-08-04 12:26:25 +08:00
rogee 897b4e018f feat(channels): add Shangwutong connector 2026-08-03 10:13:40 +08:00
Rogee 3a62f01942 fix(ui): 自定义工具表单 overflow-y-scroll→auto + 认证方式NONE翻译改为'无' + Captain文档爬虫/同步后端 2026-08-01 21:25:55 +08:00
Rogee 63df5b8b91 fix(captain): 试验场不查 FAQ 知识库 + 添加常见问题报 400
三个问题修复:

1. 添加常见问题报 400 (assistant_id 类型不匹配)
   - CreateResponseDialog.vue: route.params.assistantId 是字符串,
     传给后端 uint 字段导致 JSON 反序列化失败
   - 修复: Number(route.params.assistantId) 转为数字
   - 同时修复 POST /assistant_responses 无尾部斜杠 307 重定向问题

2. 试验场 playground 不做 RAG 检索
   - generatePlaygroundLLMResponse 只构建 system prompt + 对话历史,
     从不查 FAQ 知识库
   - 新增 retrieveFAQContext(): embed 用户问题 → pgvector 搜索 approved
     FAQ → 注入 system prompt
   - 受 feature_faq 配置开关控制

3. FAQ embedding 无法写入 (pgvector 序列化 + 维度问题)
   - pgvector stub 无 driver.Valuer, GORM Save() 报 SQLSTATE 42804
   - 新增 UpdateEmbedding() 用 ?::vector 原始 SQL 绕过
   - SimilaritySearch 排除 embedding 列 + 手动格式化向量字面量
   - embedding 列从 vector(1536) 改为 vector (跟随模型维度)
   - FAQ 创建/更新时自动索引 embedding (SetRAGService 注入)
2026-08-01 19:37:19 +08:00
Rogee 04b999e377 refactor: 移除 FakeMessagePlatform channel 全部逻辑、展示、配置
- 删除 channels/fake/ 整个 Node.js FakeMessagePlatform (8文件)
- 删除后端 FakeProvider (fake.go + fake_test.go) + FakeWebhookHandler (fake_webhook.go)
- bootstrap.go: 移除 FakeProvider 接线 + isFakeChannelEnabled()
- router.go: 移除 FakeWebhook 字段 + /webhooks/fake/:identifier 路由
- provider.go: 移除 ChannelFake 常量
- inbox_service.go: 移除 fake channel 类型验证 + isFakeChannelAllowed()
- 前端: 移除 Fake.vue + ChannelFactory/ChannelList/ChannelItem 引用 + i18n (en/zh_CN)
- package.json: 移除 fake:start/dev/test/dev:all 脚本
- pnpm-workspace.yaml: 移除 channels/fake
- .env/.env.example/quickstart: 移除 GOCHAT_ALLOW_FAKE_CHANNEL
- 测试: bridge_listener_test 改用 web_widget, router_test 移除 fake 路由断言
- 保留 fake:ai LLM Provider (backend/internal/llm/fake_provider.go) — 与 channel 无关
2026-07-30 09:09:17 +08:00
Rogee 92f0d51375 refactor: 统一 DB/Redis 配置为 DSN 模式 + 移除 Helm/K8s 部署
- DatabaseConfig: Host/Port/User/Password/Name/DBName/SSLMode → 单个 DSN 字段
- RedisConfig: Host/Port/Password/DB/URL → 单个 DSN 字段
- 环境变量: GOCHAT_DATABASE_* (7个) → GOCHAT_DATABASE_DSN, GOCHAT_REDIS_* (5个) → GOCHAT_REDIS_DSN
- validator.go: DSN URL 解析校验 (scheme + host)
- redis.go: redis.ParseURL(cfg.DSN) 直连
- 所有 docker-compose / CI / shell 脚本 / .env 同步更新
- 删除 deploy/helm/ 整个目录 (20个文件)
- CI 删除 helm-validate / deploy-staging / deploy-production 三个 job
- 文档同步更新 (README, 架构设计, PRD, 滚动升级)
2026-07-29 20:58:10 +08:00
Rogee 851ca7e372 refactor: 移除 SAML/LDAP/MFA 登录方式,仅保留本地账号密码和 OIDC
后端移除:
- SAML: auth/saml.go, handler/saml_handler.go, account_saml_settings_handler.go,
  model/account_saml_settings.go, model/saml_idp_config.go, repo/*.go
- LDAP: auth/ldap.go, handler/ldap_handler.go, model/account_ldap_settings.go,
  repo/account_ldap_settings_repo.go
- MFA: auth/mfa.go, handler/mfa_handler.go
- auth_service: 移除 mfaService 依赖、MFARequired 字段、LoginWithMFA 方法
- auth_handler: 移除 LoginMFA handler、MFA 分支逻辑
- bootstrap: 移除 SAML/LDAP/MFA service 初始化和 handler 注册
- sso_middleware: 精简为仅支持 OIDC provider
- router: 移除 SAML/LDAP/MFA 路由注册
- config: 移除 SAMLConfig/LDAPConfig struct 和 defaults

前端移除:
- v3/login: 移除 MFA 验证流程和 SAML 登录入口
- v3/api/auth: 移除 MFA 响应处理
- v3/routes: 移除 SSO login 路由
- dashboard: 移除 MFA 设置页面、SAML 安全设置页面
- i18n: 移除 mfa.json
- featureFlags: 移除 SAML feature flag

.env.example / .env: 移除 SAML/LDAP 配置段
2026-07-29 19:03:04 +08:00
Rogee fa6737e258 refactor: 精简配置体系,移除 OAuth 登录/Rate Limit/Admin env 配置
- 移除 .env.example 中 Feature Flags 段(代码中不存在这些 env var)
- 移除 Google/GitHub OAuth 登录认证代码(auth/oauth.go、auth_handler
  OAuthAuthorize/OAuthCallback 路由、auth_service OAuthLogin),保留
  Twitter/Google 作为消息渠道 provider
- 从 OAuthConfig 移除 GitHub 字段(Google 保留供 channel provider 使用)
- 移除 RateLimitConfig 可配置性,RateLimit 中间件改为硬编码 100 req/min、
  60s window,移除 config/validator/reloader 中的 rate_limit 相关代码
- 移除 .env.example 中 GOCHAT_ADMIN_EMAIL/PASSWORD 配置
- 新增 gochat init 命令:交互式或通过 --email/--password/--name flags
  初始化超级管理员账户,创建默认 Account + AccountUser 关联
2026-07-29 16:26:19 +08:00
Rogee 9816848ca2 fix: Web Widget SDK + Auto-Reply AgentBot sender + LLM 真实模型对接
## 核心修复

### 1. Auto-Reply Sender 修复(所有渠道)
- AutoReplyListener.sendAutoReply() 通过 botInboxRepo 查询 inbox 关联的 AgentBot
- 使用正确的 SenderType="AgentBot"(非小写 agent_bot)传递真实 AgentBot ID
- bootstrap 注入 agentBotInboxRepo/agentBotRepo 依赖

### 2. 事件数据 BUG 修复(影响所有 Webhook 渠道)
- incoming_persister.dispatch(): 补全 sender_type/content 到 event.Data
- channel/webhook.go: HandleWebhook 同步分发也补全 sender_type/content
- 未补全前 AutoReplyListener 找不到字段直接跳过

### 3. Web Widget SDK 生产验证修复
- cookie → localStorage token 同步(frontend/index.html)
- 路由双注册修复(router.go)
- Vite SPA 模式 + /widget 重写(vite.config.ts)
- WidgetService 注入 Dispatcher 触发事件分发

### 4. LLM 真实模型对接
- 配置 deepseek-v4-flash @ http://10.58.144.6:2014/v1
- LLM-mode auto-reply 规则创建并验证通过
- Prompt 文档落地: docs/captain-ai-auto-replay-prompt.md

### 5. 新增基础设施
- Helm chart (deploy/helm/)
- Widget SDK 生产测试页面
- QA 报告

Closes: BUG-W2 (auth sync), BUG-W3 (route double-reg),
       BUG-WEBHOOK-EVENT (missing event data fields)
2026-07-28 14:03:19 +08:00
Rogee 05c5752a2b fix: Campaign Create 400 + Reports 500 + 种子数据补全
修复:
- campaign_handler.go: Campaign创建JSON解析报VALIDATION_ERROR
- analytics_query_helpers.go: Reports标签/团队维度500(SQL query)
- bootstrap.go: 补充Campaign种子数据确保测试环境完整
2026-07-27 22:01:50 +08:00
rogee c3806b701a feat(parity): align Chatwoot 4.15.1 contracts 2026-07-14 12:11:52 +08:00
rogee 8b9eedc0e2 feat(copilot): finish configuration center 2026-07-13 14:57:28 +08:00
rogee 0a69d80f7c feat(copilot): complete runtime provider configuration 2026-07-13 14:57:28 +08:00
rogee df23caf7d9 feat(copilot): move provider configuration to settings 2026-07-12 22:27:29 +08:00
rogee f923791d39 update 2026-07-12 12:20:23 +08:00
rogee 7f2d5579ff fix: stabilize development config and account settings 2026-07-11 17:15:38 +08:00
rogee 762de6aa3b feat: migrate worker job dispatch from DB polling to Redis Streams
- worker.go: add Redis fields, XADD on Enqueue, XREADGROUP BLOCK consumer
  loop, sweep compensation for delayed/failed jobs, DB-polling fallback
  when rdb is nil, XGroupCreateMkStream for idempotent consumer groups
- config.go: extend WorkerConfig with stream_prefix, consumer_group,
  block_timeout_s, sweep_interval_s + defaults, env bindings, reloadable
- validator.go: validate new worker Redis fields
- bootstrap.go: fix concurrency bug (NewWorkerPoolWithOptions with Redis
  + cfg.Worker.Concurrency), reorder rdb init before worker pool
- config.dev.yaml/config.prod.yaml: add worker Redis params
- worker_test.go: 6 new miniredis tests (end-to-end, fallback, sweep,
  multi-consumer competition, group creation, Redis failure recovery)
- config_test.go/reloader_test.go: adapt fixtures for new fields
2026-07-10 12:56:32 +08:00
rogee 05af5ebcbc fix: harden fake channel — production guard, token validation, typing events, URL validation, capability narrowing
- Guard fake channel with GOCHAT_ENV check: skip init() registration,
  bootstrap wiring, and inbox creation in production
- Reject empty-token webhooks in production (was silently skipped)
- Use PostgreSQL jsonb @> query for inbox lookup, keep SQLite fallback
- Replace isValidURL string-prefix hack with net/url.Parse
- Handle typing.start/typing.stop by returning nil (no garbage messages)
- Narrow Capabilities to only implemented features (Attachments, Replies)
- Hide fake channel from frontend channel list in production builds
2026-07-10 10:55:54 +08:00
rogee 9c852cd99b add fake channel 2026-07-09 18:14:45 +08:00
rogee 0dabb8cfa5 docs: 整理文档目录结构 — 清理过时文档、归集功能子目录、统一命名规范
清理:
- 删除 34 份过时文档(gap reports/QA临时报告/验收报告/阶段性文档)
- 删除 docs/.hermes/skills 第三方 skills 副本(16 文件)
- 删除 skills-lock.json

目录归集:
- 根目录仅保留 README.md 索引
- product/ — 产品与架构设计(PRD + ARCHITECTURE + P2设计文档 + AI/企业路线图)
- tracking/ — Chatwoot parity 开发跟踪
- requirements/ — M01-M12 模块需求
- plans/ — 历史实现计划
- parity/ — 路由 parity 与前端契约
- qa/ — QA 报告与测试计划
- ops/ — 运维部署

命名规范:
- 全小写 kebab-case,禁止全大写文件名
- product/tracking/ops 用 NN- 序号前缀
- requirements 用 MNN- 两位零填充模块号
- plans/qa 用 YYYY-MM-DD- 日期前缀
- requirements M1-M9 零填充为 M01-M09(修复字典序)

同步更新:
- backend/cmd/route_parity/main.go 路径默认值
- backend/scripts/parity_frontend_smoke.sh 报告路径
- 所有 docs 内部交叉引用
- .gitignore 排除编译产物 (backend/gochat, backend/route_parity)
- 新增迁移 000052/000053
- 前端 WS 相关修改
2026-07-09 14:53:27 +08:00
rogee af5c7c6bc7 Phase 3.3: Multi LLM Provider support (Anthropic Claude)
- anthropic_provider.go (new): AnthropicProvider implementing the Provider
  interface using Claude's messages API. Handles:
  - System prompt as top-level param (not in messages array)
  - Content blocks response format → extract text
  - SSE streaming with Anthropic event types (content_block_delta, message_stop)
  - Anthropic-specific headers (x-api-key, anthropic-version)
  - Retry with exponential backoff (shared logic with OpenAI provider)
  - Embedding API returns error (Anthropic has no embeddings; OpenAI-compat
    provider should be used for embeddings)
- NewProviderFromConfig factory function: selects AnthropicProvider for
  provider="anthropic"/"claude", OpenAIProvider for all others
- bootstrap.go: use NewProviderFromConfig instead of hardcoded NewOpenAIProvider,
  allowing config.captain.llm_provider to switch between providers

Note: domestic providers (Volcengine/Doubao/Qwen) use OpenAI-compatible API
and work with the existing OpenAIProvider by setting llm_base_url.

Verified: go build + go vet + go test all pass
2026-07-08 15:38:08 +08:00
rogee b2f36a20a0 Phase 3.2: Function Calling — tool_call loop for AI services
- llm/provider.go: extend ChatMessage with ToolCalls, ToolCallID, Name
  fields; add ToolCall + ToolCallFunction structs for parsing LLM
  function call responses
- tool_execution_service.go (new): ToolExecutionService that converts
  CaptainCustomTool → LLM ToolDefinition, executes HTTP tool calls
  (GET/POST/PUT with bearer/basic/api-key auth), and runs the full
  tool_call loop (LLM → tool_call → execute → result → LLM → final
  answer) with maxIterations safeguard
- captain_conversation_service.go: add toolExecSvc field +
  SetToolExecutionService method; use RunToolCallLoop in
  generateConversationResponse when tools are available, with graceful
  fallback to plain LLM call on error
- bootstrap.go: instantiate ToolExecutionService and inject into
  CaptainConversationService

Verified: go build + go vet + go test all pass
2026-07-08 15:38:08 +08:00
rogee c72e359e48 Phase 3.1: Help Center semantic search with pgvector
- ArticleEmbeddingRepo (new): Upsert, GetByArticleID, DeleteByArticleID,
  SearchByEmbedding using pgvector cosine distance (vector_embedding column)
- ArticleEmbedding model: add VectorEmbedding pgvector.Vector field
  alongside existing JSONB Embedding (backward compatible)
- ArticleService: add SemanticSearch() — generates query embedding via LLM,
  searches articles by cosine similarity; add GenerateEmbedding() — creates
  and stores article embedding from title+description+content
- ArticleHandler: add SemanticSearch endpoint
  GET /portals/:portal_id/articles/semantic_search?query=...
- bootstrap.go: inject articleEmbeddingRepo + llmProvider into ArticleService
- router.go: register /articles/semantic_search route
- migration 000049: add vector(1536) column to article_embeddings table,
  create ivfflat index, migrate existing JSONB data to vector format

Verified: go build + go vet + go test all pass
2026-07-08 15:38:08 +08:00
rogee b769b9a3e4 Phase 2: AutoReplyRule integration + AgentBot Captain type
AutoReplyRule complete integration:
- bootstrap.go: instantiate AutoReplyRuleService + AutoReplyListener,
  register listener on channel dispatcher for message.created events
- router.go: register /captain/auto_reply_rules CRUD + /evaluate routes
- auto_reply_rule_handler.go: fix c.Param(id) → c.Param(account_id),
  override evalCtx.AccountID from path param
- auto_reply_rule_service.go: add JSON tags to AutoReplyEvaluationContext
  for correct request body binding
- auto_reply_listener.go (new): EventListener that triggers on incoming
  messages, evaluates active rules, composes reply (static/LLM/mixed),
  respects DelaySeconds and OneTimeOnly flags, sends via MessageService
- migration 000048: create captain_auto_reply_rules table

AgentBot + Captain integration:
- agent_bot_listener.go: add captainConvSvc field + SetCaptainConversationService
  method. In HandleEvent loop, check bot.BotType == captain and route
  to CaptainConversationService.BuildConversationResponseByAccount
  instead of webhook push. Extract assistant_id from bot.Config JSONB,
  extract conversation_id from event data.
- bootstrap.go: inject captainConversationService into agentBotListener

CaptainConversationService improvement:
- generateConversationResponse: use assistant config for system prompt,
  model name, and temperature instead of hardcoded values

Verified:
- go build ./... passes
- go vet passes on all internal packages
- go test passes (service + repository + llm, SQLite mode)
- Auto-reply CRUD: create/get/update/delete all work
- Auto-reply evaluate: correctly matches hello → should_reply=true,
  correctly rejects non-matching message
- Existing routes unaffected (assistants, RAG, conversation respond)
- Migration 000048 creates captain_auto_reply_rules table successfully
2026-07-08 15:38:08 +08:00
rogee 42b8b6c7f9 Activate Captain AI features: config, RAG routes, conversation handler
Phase 1 of AI_FEATURE_ROADMAP.md:

1. config.yaml: Add captain configuration section (llm_provider, llm_model,
   llm_api_key, llm_base_url, embedding_model, embedding_dims, max_tokens,
   temperature). Secrets injected via GOCHAT_CAPTAIN_LLM_API_KEY env var.

2. RAG route registration:
   - bootstrap.go: instantiate RAGService + RAGHandler, add to Handlers
   - router.go: register POST /captain/rag/query + /captain/rag/index/:response_id
   - rag_handler.go: fix account_id param name (was "id", route uses "account_id")

3. CaptainConversationService activation:
   - Remove "_ = captainConversationService" ignore in bootstrap.go
   - Create CaptainConversationHandler with BuildResponse endpoint
   - Register POST /captain/conversations/:conversation_id/respond route
   - Fix account_id param name in handler

Verified:
- go build ./... passes
- go vet passes on all modified packages
- go test passes (llm + service packages)
- Server starts with captain config loaded
- RAG query/index routes return proper handler responses (not 404)
- Conversation respond route returns proper skip for non-pending conversations
- Existing captain routes unaffected (assistants list still works)
2026-07-08 15:38:08 +08:00
rogee e61b2acf6d Bridge channel dispatcher events to WebSocket EventPublisher for real-time delivery 2026-07-08 09:02:44 +08:00
rogee aeddedf2a3 Reorganize repo: backend/, deploy/, docs/ layout + AGENTS.md
Restructure the monorepo into clear top-level directories:
- backend/: Go module root (cmd, internal, pkg, configs, migrations,
  docs/swagger, scripts, tests, go.mod, Makefile, .air.toml)
- deploy/: Docker (Dockerfile, docker-compose*), quickstart, fluentd
- docs/: project documentation + reports/ (moved from repo root)
- AGENTS.md: new AI coding-agent guide at repo root

Update all references to the new layout:
- Dockerfile: COPY backend/go.mod, COPY backend/ (context = repo root)
- docker-compose files: context ../.., dockerfile deploy/docker/Dockerfile,
  env_file ../../.env, volume mounts ../../backend:/app
- deploy/quickstart/compose.yaml: dockerfile deploy/docker/Dockerfile
- CI: working-directory: backend for go commands, file deploy/docker/Dockerfile,
  coverage path backend/coverage.out, health_check backend/scripts/
- backend/Makefile: docker target uses -f ../deploy/docker/Dockerfile ../
- README: architecture tree, quickstart, config paths updated

Move root stray scripts (rename_models.*, run_m11_tests.sh, verify_build.sh,
gorm_bool_main.go) to backend/scripts/legacy/. All moves via git mv to
preserve history. Build, vet, SQLite tests, and docker compose config verified.
2026-07-07 14:44:12 +08:00