qyyfw/qihuaiflow
1
0 Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
244 Commits 1 Branch 24 Tags
037c965c26b635a97b36266e6646e0c13289e806
Commit Graph
100 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
QihuAI Design 037c965c26 feat(engine): #873 dual-Claw event contract + SseAdapter/BufferAdapter + chat.py SSE delegate + im_llm EngineCore thin-shell (gray-gated) 
- app/core/engine_event.py (#880): EngineEvent dataclass + make_* factories, single construction entry, byte-compatible wire with legacy ChatPage.tsx
- app/core/claw_adapters.py (#884): SseAdapter (hot frames zero-metadata, terminal keeps trace_id) + BufferAdapter (assemble() preserves __media__)
- app/api/chat.py (#881): /messages/stream now delegates to SseAdapter; wire bytes unchanged (46B delta / done+message_id)
- app/api/im_llm.py (#883): IM_USE_ENGINE_CORE gray gate; _call_engine_core reuses EngineCore via BufferAdapter (default OFF, preserves media fast-path)
- app/api/chat_service.py: capture 3 container-ahead fixes (stray import asyncio removed, logger.info format, LiteLLM master key)
 2026-08-04 12:25:12 +08:00
QihuAI Design 34648e4810 fix(im_bot): segment long WeChat text replies + enhance send diagnostics (#878)\n\niLink returns HTTP 200 but WeChat silently drops long messages (1698-char\nHTML image link, 3011-char skill list). Add WECHAT_TEXT_MAX_LEN=1500 and\nsegment long text into multiple items. Also log payload item lengths and\nmedia URL lengths for future diagnosis. 2026-08-04 11:14:02 +08:00
QihuAI Design f4e18bafe4 test: add R-DUAL dual-Claw regression sentinel (#873) - always-on guards for IM unified discovery / Web-IM parity / naming single-source; opt-in live MCP reachability; R-DUAL-3/6 pending 2026-08-04 10:42:45 +08:00
QihuAI Design 29a1ce2e54 fix: 双Claw能力对齐 + MCP/LLM代理绕过（P0止血） 
- 新增 app/core/capability_discovery.py：统一能力发现层，Web/IM 双Claw共用单一实现
  （三级降级：用户安装 → 平台published → 相关性裁剪；MCP 自动挂载已启用服务）
- im_llm.py：IM Bot Claw 改用统一发现层，恢复 skills(12) + MCP(26工具) 能力，
  修复 #866 部署回退导致的 agents=[]/mcp=[] 回归；mcp__ 前缀分流到 call_mcp_tool
- mcp_client.py：注入 httpx_client_factory(trust_env=False) 绕过容器 HTTP_PROXY，
  修复外部 MCP(xiaobenyang.com / anysearch.com) tools/list 全部静默失败（mcp_tools 0→26）
- llm_client.py / im_bot_user.py：2026-07-31 代理劫持内部请求 + 媒体断连修复（随镜像已上线）
 2026-08-04 10:21:19 +08:00
QihuAI Design 9a43ee244d fix(im_llm): 代理绕过Docker内部hostname 2026-07-31 08:51:15 +08:00
QihuAI Design 96aabc31f6 feat: mumuainovel app service infrastructure (db+compose+nginx) 2026-07-28 11:41:40 +08:00
QihuAI Design a9d8642db5 phase2-risk-loop-mempalace
CI / gate (push) Has been cancelled
Details
2026-07-28 09:18:16 +08:00
QihuAI Design 88b9a232ce fix-frontend-3-items-complete
CI / gate (push) Has been cancelled
Details
2026-07-28 06:31:48 +08:00
QihuAI Design 1633d5c33e phase1-agent-canvas-done
CI / gate (push) Has been cancelled
Details
2026-07-27 23:20:22 +08:00
QihuAI Design 96be3fdeb3 phase1-final
CI / gate (push) Has been cancelled
Details
2026-07-27 22:27:56 +08:00
QihuAI Design 52f1770515 phase1-complete-billing-skillruntime 2026-07-27 18:16:28 +08:00
QihuAI Design 89ce7d80dc phase1-billing-skillruntime 2026-07-27 18:14:57 +08:00
QihuAI Design 65440d91ee phase1-billing-meilisearch 2026-07-27 17:05:21 +08:00
QihuAI Design 1e0bd6f7a2 phase1-skillmd-v2-schema 2026-07-27 16:55:48 +08:00
QihuAI Design a336ac283d phase0-litellm-deployed-via-hk-proxy 2026-07-27 15:54:28 +08:00
QihuAI Design cf8c955d45 phase0-containers-meilisearch-litellm
CI / gate (push) Has been cancelled
Details
2026-07-27 11:09:49 +08:00
QihuAI Design 245484a0c5 phase0-final-rls-rbac-complete
CI / gate (push) Has been cancelled
Details
2026-07-27 09:57:55 +08:00
QihuAI Design 2068421d41 phase0-fix-auth-order-db-migration 2026-07-27 09:54:03 +08:00
QihuAI Design 7b1941fdaf phase0-multi-tenant-rls-rbac 2026-07-27 09:44:06 +08:00
QihuAI Design f9c8bda6e0 docs-add-iteration-plan
CI / gate (push) Has been cancelled
Details
2026-07-27 09:26:16 +08:00
QihuAI Design ec7de645f4 docs-add-architecture-blueprint
CI / gate (push) Has been cancelled
Details
2026-07-27 09:10:11 +08:00
QihuAI Design efa63f9d25 fix-overflow-x-horizontal-scroll
CI / gate (push) Has been cancelled
Details
2026-07-27 08:54:39 +08:00
QihuAI Design c624d8f37c mimo-token-plan-adapter
CI / gate (push) Has been cancelled
Details
2026-07-26 21:47:48 +08:00
QihuAI Design bb32884ecb p2-mcp-schema-error-step-enhancements
CI / gate (push) Has been cancelled
Details
2026-07-26 20:59:52 +08:00
QihuAI Design df67a298be mcp-tool-naming-fix
CI / gate (push) Has been cancelled
Details
2026-07-26 15:37:17 +08:00
QihuAI Design e1e50e884e feat(chat): align AI tool-use with GPT-4.1/Anthropic standards -- Fix1: AGENT_GUIDE in system prompt (Persistence/Tool-calling/Planning), Fix2: install_app def improved, Fix3: max_tool_rounds 5->15
CI / gate (push) Has been cancelled
Details
2026-07-26 08:35:42 +08:00
QihuAI Design a2504bce34 fix(chat): resolve Auto-route failover event-loop freeze (#812) 
Root cause: ensure_structured_column() executed a synchronous blocking
engine.connect().execute(SELECT information_schema.columns ...) inside the
async request path (_build_chat_history / _maybe_compress_history), freezing
the uvicorn event loop and hanging all endpoints (~200s, recovered only by
docker restart).

Fix:
- chat_context.py: remove per-request ensure_structured_column() calls; run
  once idempotently at app startup (main.py lifespan). Use CURRENT_DATABASE()
  for PostgreSQL compatibility.
- main.py: add startup-only ensure_structured_column() hook (try/except).
- llm_client.py: trust_env=False + bounded httpx.Timeout/wait_for so broken
  endpoints fail fast instead of hanging the event loop.
- chat_service.py: run media generation in a background daemon thread with its
  own event loop (_launch_media_task_bg) so SSE end does not cancel image/video
  tasks (#811); remove TEMP faulthandler diagnostic.

Safe-align: persist accumulated live container changes (admin/*, knowledge,
market, models, config, observability, mcp_client, platform_knowledge,
im_bot_platform, chat_media, capability_registry, requirements) and add
workflow_templates.

Verified: live failover test (model-006 -> conn-refused) returns in ~1.9s with
concurrent login 0.83s/200; event-loop responsiveness restored (sub-second).
 2026-07-26 00:35:35 +08:00
QihuAI Design 394a7786e0 chore: remove MySQL service from docker-compose (PostgreSQL migration complete)\n\n- Drop dead mysql service, mysql_data volume, and aiflow depends_on: mysql\n- Remove unused MYSQL_* env vars from aiflow service\n- Retain DATABASE_URL/POSTGRES_* pointing at qihu-aiflow-pg18\n- Closes the MySQL teardown started in task #802
CI / gate (push) Has been cancelled
Details
2026-07-25 20:59:44 +08:00
QihuAI Design 640edc4970 chore: normalize tsconfig.json line endings (file missed by prior commit)
CI / gate (push) Has been cancelled
Details 
The earlier renormalize commit (771c845) missed frontend/tsconfig.json; this
completes the LF normalization so all tracked text files are LF. .gitattributes
(* text=auto eol=lf) prevents future CRLF.
 2026-07-25 12:33:53 +08:00
QihuAI Design 771c8456b8 chore: normalize line endings to LF via .gitattributes 
Root-cause fix for mixed CRLF/LF in the repo (no .gitattributes previously).
Adds '* text=auto eol=lf' and explicit binary rules so all future checkouts
are LF. Renormalizes all tracked text files (no logical content change).
Backup tags: image qihuaiflow:backup-lineend-20260725-121632, git backup-lineend-pre-20260725-121632.
 2026-07-25 12:16:39 +08:00
QihuAI Design 2a7bb875f9 fix(mcp/chat): root-cause fixes for AnySearch MCP test + URL app install 
- mcp_admin.py: replace get_event_loop().run_until_complete() with asyncio.run() in _test_mcp_server worker-thread path (RuntimeError: no current event loop in thread). Fixes backend AnySearch 'test failed'.
- chat_skill.py: add synchronous _execute_install_app() that auto-detects skill/mcp/agent from a URL and creates MarketApp(+MCPServer is_enabled=True for mcp) + AppInstallation. No running-loop asyncio call (called sync from chat dispatch).
- chat_service.py: register 'install_app' function_definition and dispatch branch so the AI chat can install skills/mcp/agent by URL.
Image already persisted via docker export/import (qihuaiflow:with-deps=aaf6fe67cde8) because base image was pruned and docker commit failed.
 2026-07-25 11:51:19 +08:00
QihuAI Design 256d9f33e6 chore(align): sync Git with running container as authoritative source 
Phase 0 SSE 流式聊天 landed in the running container and captured in Git so
the three sources (container := image := Git) agree.

Phase 0 — SSE 流式聊天（Web 端，IM bot 路径保持不变、共用引擎）:
- app/api/chat.py: 新增独立 SSE 端点
  POST /app/api/chat/conversations/{conv_id}/messages/stream
  基于 asyncio.Queue + create_task 将 _send_message_core 桥接为
  text/event-stream 生成器，吐出 delta / reasoning / done / error 事件
- app/api/chat_service.py: _send_message_core 增加 stream + on_event 参数；
  普通（无工具）聊天 round-0 主调用走 achat_complete(stream=True) 流式；
  done 事件携带 message_id / content / process_steps / used_skills /
  used_mcp / generating
- app/core/llm_client.py: 修复 _create_kwargs 硬编码 stream=False 的根因 bug
  （流式调用传 stream=True 导致 TypeError: multiple values for keyword），
  现 _create_kwargs(request_body, stream=True) 字段随参数变化
- frontend/src/pages/front/ChatPage.tsx + ChatPage.css + types/index.ts:
  发消息改为 fetch SSE 消费，实时增量渲染 AI 回复文本与思考链(reasoning)，
  done 事件用 message_id 定稿并渲染过程步骤；网络/流式失败自动回退非流式

Alignment performed 2026-07-24 18:25:11. No deletions; secrets/venv/node_modules/
caches were not touched (tracked-source-only copy).
 2026-07-24 18:25:15 +08:00
QihuAI Design 3788a93425 chore(align): sync Git with running container as authoritative source 
Phase 0 SSE 流式聊天 landed in the running container and captured in Git so
the three sources (container := image := Git) agree.

Phase 0 — SSE 流式聊天（Web 端，IM bot 路径保持不变、共用引擎）:
- app/api/chat.py: 新增独立 SSE 端点
  POST /app/api/chat/conversations/{conv_id}/messages/stream
  基于 asyncio.Queue + create_task 将 _send_message_core 桥接为
  text/event-stream 生成器，吐出 delta / reasoning / done / error 事件
- app/api/chat_service.py: _send_message_core 增加 stream + on_event 参数；
  普通（无工具）聊天 round-0 主调用走 achat_complete(stream=True) 流式；
  done 事件携带 message_id / content / process_steps / used_skills /
  used_mcp / generating
- app/core/llm_client.py: 修复 _create_kwargs 硬编码 stream=False 的根因 bug
  （流式调用传 stream=True 导致 TypeError: multiple values for keyword），
  现 _create_kwargs(request_body, stream=True) 字段随参数变化
- frontend/src/pages/front/ChatPage.tsx + ChatPage.css + types/index.ts:
  发消息改为 fetch SSE 消费，实时增量渲染 AI 回复文本与思考链(reasoning)，
  done 事件用 message_id 定稿并渲染过程步骤；网络/流式失败自动回退非流式

Alignment performed 2026-07-24 16:28:19. No deletions; secrets/venv/node_modules/
caches were not touched (tracked-source-only copy).
 2026-07-24 16:28:19 +08:00
QihuAI Design e8a1791c9f chore(align): sync Git with running container as authoritative source 
Standards alignment (STANDARDS_AUDIT_2026-07-24): Phase 1 标准化核心 +
Phase 2 质量层 landed in the running container and captured in Git so the
three sources (container := image := Git) agree.

Backend (Phase 1 标准化核心):
- mcp_client.py: replaced hand-rolled JSON-RPC with official `mcp` SDK
  (ClientSession, streamable_http/sse transports, protocol auto-negotiation)
- core/otel.py + core/observability.py: standard OpenTelemetry SDK bridge
  (OTLP gRPC), wired to Grafana Alloy (qihu-aiflow-alloy:4317) which forwards
  metrics to Prometheus; emits aiflow_span_duration_ms / aiflow_span_count
- deployments: Grafana Alloy container + Prometheus remote-write receiver

Backend (Phase 2 质量层):
- core/rag_pipeline.py: standardized RAG (recursive overlap chunking +
  rerank hook) reusing pgvector_search
- core/llm_client.py: SDK-ified LLM + embeddings (aembed/embed) collapsing
  hand-rolled httpx calls; trust_env=False to bypass container proxy

Migrations:
- 018_normalize_marketapp_scene.sql: fixed capability allowlist
  (prevents capability wipe on restart)

Alignment performed 2026-07-24 12:18:51. No deletions; secrets/venv/node_modules/
caches were not touched (tracked-source-only copy).
 2026-07-24 12:18:52 +08:00
QihuAI Design acde481bed chore(align): sync Git with running container as authoritative source 
One-time alignment to close drift between the running container
(qihu-aiflow / image qihuaiflow:with-deps) and this Git repository.
Container hotfixes previously persisted only via `docker commit` are now
captured in Git so Git becomes the single source of truth.

Backend:
- chat_service.py: accumulated fixes incl. EigenFlux README guidance
- chat_context.py / chat_media.py: URL/web-repo context injection
- api/url_reader.py: NEW SSRF-safe web/README reader (Issue #725)
- skills_admin.py & Skills.tsx: 14-scene capability unification
- pgvector_search.py, orchestrator.py, platform_knowledge.py,
  market.py, admin/models.py: drift sync

Frontend:
- ChatPage.tsx: collapsible AI think/act block (Issue #724)
- MarketPage / EvolutionDashboard / TokenDashboard styling sync

Migrations:
- 018_normalize_marketapp_scene.sql: fixed capability allowlist
  (prevents capability wipe on restart)

Alignment performed 2026-07-24 07:44:19. No deletions; secrets/venv/node_modules/
caches were not touched (tracked-source-only copy).
 2026-07-24 07:44:19 +08:00
QihuAI Design 26075272d6 chore(align): sync Git with running container as authoritative source 
One-time alignment to close drift between the running container
(qihu-aiflow / image qihuaiflow:with-deps) and this Git repository.
Container hotfixes previously persisted only via `docker commit` are now
captured in Git so Git becomes the single source of truth.

Backend:
- chat_service.py: accumulated fixes incl. EigenFlux README guidance
- chat_context.py / chat_media.py: URL/web-repo context injection
- api/url_reader.py: NEW SSRF-safe web/README reader (Issue #725)
- skills_admin.py & Skills.tsx: 14-scene capability unification
- pgvector_search.py, orchestrator.py, platform_knowledge.py,
  market.py, admin/models.py: drift sync

Frontend:
- ChatPage.tsx: collapsible AI think/act block (Issue #724)
- MarketPage / EvolutionDashboard / TokenDashboard styling sync

Migrations:
- 018_normalize_marketapp_scene.sql: fixed capability allowlist
  (prevents capability wipe on restart)

Alignment performed 2026-07-23 22:42:43. No deletions; secrets/venv/node_modules/
caches were not touched (tracked-source-only copy).
 2026-07-23 22:42:46 +08:00
QihuAI Design a1fd8b074d chore(align): sync Git with running container as authoritative source 
One-time alignment to close drift between the running container
(qihu-aiflow / image qihuaiflow:with-deps) and this Git repository.
Container hotfixes previously persisted only via `docker commit` are now
captured in Git so Git becomes the single source of truth.

Backend:
- chat_service.py: accumulated fixes incl. EigenFlux README guidance
- chat_context.py / chat_media.py: URL/web-repo context injection
- api/url_reader.py: NEW SSRF-safe web/README reader (Issue #725)
- skills_admin.py & Skills.tsx: 14-scene capability unification
- pgvector_search.py, orchestrator.py, platform_knowledge.py,
  market.py, admin/models.py: drift sync

Frontend:
- ChatPage.tsx: collapsible AI think/act block (Issue #724)
- MarketPage / EvolutionDashboard / TokenDashboard styling sync

Migrations:
- 018_normalize_marketapp_scene.sql: fixed capability allowlist
  (prevents capability wipe on restart)

Alignment performed 2026-07-23 22:16:24. No deletions; secrets/venv/node_modules/
caches were not touched (tracked-source-only copy).
 2026-07-23 22:16:25 +08:00
QihuAI Design 2721da5d4c feat: 思考过程展示优化 — 先展开再自动收拢 
AiProcessBlock 改进:
- 超时从 2.6s 延至 6s，用户有充足时间阅读思考链路
- 新增 aiProcessPulse 脉冲高亮动画，强调'思考过程刚出炉'
- 展开时自动 scrollIntoView，确保不被正文遮挡
- 摘要文案改为'AI 思考 / 执行过程（N步 — 自动收拢中...）'

CSS 新增:
- .ai-process-fresh 脉冲动画 + summary 文字高亮
- @keyframes aiProcessPulse: 0→50%→100% 边框扩散+收拢
 2026-07-23 22:00:49 +08:00
QihuAI Design 9d67b0544c chore(align): sync Git with running container as authoritative source 
One-time alignment to close drift between the running container
(qihu-aiflow / image qihuaiflow:with-deps) and this Git repository.
Container hotfixes previously persisted only via `docker commit` are now
captured in Git so Git becomes the single source of truth.

Backend:
- chat_service.py: accumulated fixes incl. EigenFlux README guidance
- chat_context.py / chat_media.py: URL/web-repo context injection
- api/url_reader.py: NEW SSRF-safe web/README reader (Issue #725)
- skills_admin.py & Skills.tsx: 14-scene capability unification
- pgvector_search.py, orchestrator.py, platform_knowledge.py,
  market.py, admin/models.py: drift sync

Frontend:
- ChatPage.tsx: collapsible AI think/act block (Issue #724)
- MarketPage / EvolutionDashboard / TokenDashboard styling sync

Migrations:
- 018_normalize_marketapp_scene.sql: fixed capability allowlist
  (prevents capability wipe on restart)

Alignment performed 2026-07-23 19:43:56. No deletions; secrets/venv/node_modules/
caches were not touched (tracked-source-only copy).
 2026-07-23 19:43:56 +08:00
QihuAI Design 4a95657030 chore(align): sync Git with running container as authoritative source 
One-time alignment to close drift between the running container
(qihu-aiflow / image qihuaiflow:with-deps) and this Git repository.
Container hotfixes previously persisted only via `docker commit` are now
captured in Git so Git becomes the single source of truth.

Backend:
- chat_service.py: accumulated fixes incl. EigenFlux README guidance
- chat_context.py / chat_media.py: URL/web-repo context injection
- api/url_reader.py: NEW SSRF-safe web/README reader (Issue #725)
- skills_admin.py & Skills.tsx: 14-scene capability unification
- pgvector_search.py, orchestrator.py, platform_knowledge.py,
  market.py, admin/models.py: drift sync

Frontend:
- ChatPage.tsx: collapsible AI think/act block (Issue #724)
- MarketPage / EvolutionDashboard / TokenDashboard styling sync

Migrations:
- 018_normalize_marketapp_scene.sql: fixed capability allowlist
  (prevents capability wipe on restart)

Alignment performed 2026-07-23 16:04:25. No deletions; secrets/venv/node_modules/
caches were not touched (tracked-source-only copy).
 2026-07-23 16:04:26 +08:00
QihuAI Design d3d8d62b94 fix(media): repair JSON_CONTAINS auto-routing + reconcile stale backend tests
CI / gate (push) Has been cancelled
Details 
Real bug:
- capability_registry.resolve_auto_model and chat_media._build_media_route used
  `Column.op("JSON_CONTAINS")(col, val)`, but SQLAlchemy's op() accepts only ONE
  argument -> TypeError on every image/video/audio auto-route, silently failing
  media generation (caught as "后台生成异常"). Replaced with func.json_contains().

Test reconciliation (no production behavior change):
- tests/test_context_engine.py: tiktoken upgrade made the hardcoded len//2 token
  estimates wrong; relax to tokenizer-agnostic assertions and add
  structured_memory=None to the _Summary mock (code now branches on it).
- tests/test_regression_r1r2r3.py: R3 FakeModel lacked `name` (code reads m.name);
  also the assertion assumed a literal '超时' string, but the failover architecture
  catches model-level exceptions and writes a user-understandable error marker
  instead. Align the assertion to the real contract: a media failure/timeout must
  be written back as a user-understandable error message, never left as '生成中…'.

CI gate: 28 backend pytest + 15 frontend vitest all green.
 2026-07-23 09:16:31 +08:00
QihuAI Design a08ec87b22 chore(align): sync Git with running container as authoritative source 
One-time alignment to close drift between the running container
(qihu-aiflow / image qihuaiflow:with-deps) and this Git repository.
Container hotfixes previously persisted only via `docker commit` are now
captured in Git so Git becomes the single source of truth.

Backend:
- chat_service.py: accumulated fixes incl. EigenFlux README guidance
- chat_context.py / chat_media.py: URL/web-repo context injection
- api/url_reader.py: NEW SSRF-safe web/README reader (Issue #725)
- skills_admin.py & Skills.tsx: 14-scene capability unification
- pgvector_search.py, orchestrator.py, platform_knowledge.py,
  market.py, admin/models.py: drift sync

Frontend:
- ChatPage.tsx: collapsible AI think/act block (Issue #724)
- MarketPage / EvolutionDashboard / TokenDashboard styling sync

Migrations:
- 018_normalize_marketapp_scene.sql: fixed capability allowlist
  (prevents capability wipe on restart)

Alignment performed 2026-07-23 05:42:47. No deletions; secrets/venv/node_modules/
caches were not touched (tracked-source-only copy).
 2026-07-23 05:42:48 +08:00
QihuAI Design 49f7503978 fix(models): widen market_apps.skill_content to MEDIUMTEXT for large SKILL.md 2026-07-22 12:42:43 +08:00
QihuAI Design 6da8c3938e fix(admin/mcp): prevent unnecessary wrapping in table headers and badges 2026-07-22 08:54:03 +08:00
QihuAI Design 6d06f9165c feat(skills): auto-tag+classify existing 60 skills, auto-tag on import, 409 uniqueness check, add tags column to admin 2026-07-22 07:58:40 +08:00
QihuAI Design 46528eddbb fix(market): 补齐MarketApp ORM category/tags字段 + 硬化导入管道(空内容兜底生成SKILL.md + GitHub直链归一) 2026-07-21 20:25:55 +08:00
QihuAI Design 97125d7b65 T4: AnySearch 改为全局固定配置 + 修复外部服务弹窗 UI 2026-07-21 19:27:27 +08:00
QihuAI Design 3c9d9518b1 T4: AnySearch 联网检索接入 (anysearch_client trust_env直连 NO_PROXY, kb_router use_web RRF融合, chat_context 自动注入联网上下文, admin 支持 anysearch 服务类型, 新增 POST /api/knowledge/web-search 端点) 2026-07-21 18:29:51 +08:00
QihuAI Design be7d792dc2 T3: TreeSearch 结构化文档两级检索 (build_kb_tree + tree_search BM25+向量融合, 接入 kb_router 为 tree_chunk 源, 新增 GET /api/knowledge/tree-search) 2026-07-21 12:56:57 +08:00
QihuAI Design 75f53a7e8a fix: 文生图/视频测试连接走媒体端点直连(_proxy_for_url 增加 images/videos 直连规则)，绕过智能路由代理重置长连接导致的 Server disconnected；gpt-image-2/agnes 测试连接恢复。配合 models.py 的 1024x1024 size 与 chat_media.py 的 failover 路由(默认模型第一顺位)。 2026-07-20 22:26:30 +08:00
QihuAI Design 0b00d6da45 fix: 文生图连接测试 size 1024x1024 + 媒体端点智能推导 + 图像/视频模型 failover 路由(默认模型第一顺位) 2026-07-20 22:11:53 +08:00
QihuAI Design 7674729804 test(frontend): extract Markdown renderer to utils/markdown.ts + add vitest regression tests
CI / gate (push) Has been cancelled
Details
2026-07-20 20:32:36 +08:00
QihuAI Design 11b80b90f4 fix(migrations): MariaDB 兼容幂等化 privacy_mode 列与 distributions 种子插入
CI / gate (push) Has been cancelled
Details
2026-07-20 19:37:57 +08:00
QihuAI Design 71a6403e5b fix: 加宽 skill_trajectory_links.atom_id 列 VARCHAR(36)->128 修复 DataError(1406)；TraceIdFilter 从 root logger 移至 handler 修复子 logger %(trace_id)s KeyError 日志刷屏；evolution scheduler 循环增加 db.rollback() 兜底；附带 models.py CRLF->LF 归一。
CI / gate (push) Has been cancelled
Details
2026-07-20 19:02:40 +08:00
QihuAI Design 5def2697de fix(chat): image send 500 + table/newline formatting (v2026.07.20.1708)
CI / gate (push) Has been cancelled
Details
2026-07-20 17:08:20 +08:00
QihuAI Design 612ce37518 audit fixes: align all frontend timestamps to Beijing time + debounce MarketPage search (vv2026.07.20.1)
CI / gate (push) Has been cancelled
Details
2026-07-20 15:38:55 +08:00
QihuAI Design d55a496ff4 Phase 4.3 ACA: MCP.tsx protocol selector panel + api ACA methods (v2026.07.19.12)
CI / gate (push) Has been cancelled
Details
2026-07-20 14:45:21 +08:00
QihuAI Design 72d6f9ab66 Phase 4.1+: mermaid diagrams + YAML workflow buttons + agents API (v2026.07.19.11)
CI / gate (push) Has been cancelled
Details
2026-07-20 09:24:40 +08:00
QihuAI Design 79c27795a8 Phase 4.2+4.3: YAML workflow spec + ACA protocol abstraction (v2026.07.19.10)
CI / gate (push) Has been cancelled
Details
2026-07-19 20:17:49 +08:00
QihuAI Design c716dab851 Phase 4.1+: expose version/verified/security_scan/dependencies in admin get_all_apps
CI / gate (push) Has been cancelled
Details
2026-07-19 19:29:48 +08:00
QihuAI Design 669c16b0a0 Phase 4.1: 技能市场安检引擎 + 版本化 + 绿标 (v2026.07.19.9)
CI / gate (push) Has been cancelled
Details
2026-07-19 19:15:35 +08:00
QihuAI Design 71fc502a92 Phase 3.3 前端: 后台 Agent 编排图 JSON 编辑器(载入/校验/保存/清除/示例)
CI / gate (push) Has been cancelled
Details
2026-07-19 16:55:20 +08:00
QihuAI Design 96b3f0af37 Phase 3.3 多 Agent 编排图引擎: orchestration JSON 列 + 拓扑并行引擎 + local/external/reduce 节点 + 工具沙箱继承 + 后台编排 API
CI / gate (push) Has been cancelled
Details
2026-07-19 16:41:27 +08:00
QihuAI Design 3b34ba78b8 feat(agents): Phase3.2 Agent凭据Fernet加密存储 写入加密+调用点解密+返回脱敏+主密钥持久化防竞态 [v2026.07.19.7]
CI / gate (push) Has been cancelled
Details
2026-07-19 15:27:15 +08:00
QihuAI Design 0600c37b9e feat(agents): Phase3.1 工具/MCP权限沙箱(tool_policy) 白名单+预算熔断+每轮上限+后台管理UI [v2026.07.19.6]
CI / gate (push) Has been cancelled
Details
2026-07-19 12:34:40 +08:00
QihuAI Design 2969544d54 feat(observability): Phase2.3 媒体/LLM 可观测面板(后端归因聚合+前端页) 并修复 token_usage_logs trace_id 写入(chat_service/im_llm) [v2026.07.19.5]
CI / gate (push) Has been cancelled
Details
2026-07-19 10:18:14 +08:00
QihuAI Design 491f31cead refactor(context): Phase2 上下文引擎升级 分层记忆+压缩+隔离 [v2026.07.19.4]
CI / gate (push) Has been cancelled
Details
2026-07-19 09:29:57 +08:00
QihuAI Design a7a57f9a03 refactor(observability): Phase2.2 成本归因 trace_id列+token日志写入+LLM/MCP/媒体子span [v2026.07.19.3]
CI / gate (push) Has been cancelled
Details
2026-07-19 08:51:28 +08:00
QihuAI Design 6aefdfa5c2 refactor(observability): Phase2.1 统一可观测基座 trace_id+结构化日志+span计时 [v2026.07.19.2]
CI / gate (push) Has been cancelled
Details
2026-07-19 07:47:25 +08:00
QihuAI Design 1b6a184d27 refactor(chat): split 10070-line monolith into 8 service submodules (Phase1) [v2026.07.19.1]
CI / gate (push) Has been cancelled
Details
2026-07-19 00:59:03 +08:00
QihuAI Design 4167e23e50 ci: add minimal CI gate (pre-push hook + ci_gate.py + dormant Gitea workflow) [v2026.07.18.5]
CI / gate (push) Has been cancelled
Details
2026-07-19 00:01:07 +08:00
QihuAI Design dd10245ad5 test: 前端 vitest 测试基建 (Phase0) — 北京时间渲染回归 4 用例全绿 2026-07-18 23:47:21 +08:00
QihuAI Design 1744ff40ce test: 回归用例 R1/R2/R3 固化三个反复问题 (Phase0) — 9 用例全绿 2026-07-18 23:36:01 +08:00
QihuAI Design 13578ba4c2 test: 后端 pytest 测试基建 (Phase0) — 6 用例全绿 + 部署前备份SOP合规 2026-07-18 23:29:55 +08:00
QihuAI Design 9e9c506ba9 release: v2026.07.18.1 (prod) — Phase0 工程纪律止血：部署前镜像备份SOP + 版本号规范 + 测试基建 2026-07-18 23:19:18 +08:00
QihuAI Design 1ea7ea352f chore: remove accidental .bak file 2026-07-18 13:54:19 +08:00
QihuAI Design d593d8dc42 fix: 显式选中技能/MCP 时优先按工具资料回答 + 媒体任务超时/日志 
- _build_system_prompt 末尾增加【最高优先级覆盖规则】：用户明确选择技能/MCP 并询问其介绍/功能/用法时，
  必须只基于该工具资料作答，禁止引用平台知识库中技能市场/MCP/平台能力的通用描述。
- _generate_media_task 增加启动/结束日志，对图像生成加 90s 超时、视频 300s 超时，避免异步任务挂死导致前端一直显示“生成中”。
 2026-07-18 13:52:26 +08:00
QihuAI Design 1578d68f95 fix: 修复前台4项问题(MCP列举/微信技能上限/Word资产栏/技能MCP反馈) + 同步容器live状态 
- #549 平台MCP列举: 注入全量已启用MCP清单, AI不再凭空编造
- #550 微信Bot技能自动发现上限 15->300
- #551 知识库Word文档同步资产后Word栏可见 + 双向删除同步(assets/knowledge级联软删)
- #552 对话反馈实际使用的技能/MCP(used_mcp字段), 含历史消息序列化
- 同步容器内其他未提交live改动(im_bot_platform/TokenDashboard/WechatBot/ChatPage)
 2026-07-18 08:06:37 +08:00
QihuAI Design 7fb7c07f57 fix(admin/skills): 支持删除从市场导入的 MarketApp 技能 2026-07-17 22:25:47 +08:00
QihuAI Design cc35c61fbd fix: 技能市场分类映射缺失+筛选chip激活态配色；聊天显式选中技能时正确介绍技能并精简回复排版 2026-07-17 21:45:30 +08:00
QihuAI Design f8d1c18927 fix(admin): 后台未登录访问 Skills/MCP/Agent 报 Not authenticated\n\n- AdminLayout 增加登录+管理员守卫，无 token 或非 admin 跳 /login\n- api request() 处理 403 Not authenticated/需要管理员权限，清 token 跳登录\n- 根因：FastAPI HTTPBearer 无 token 返回 403 而非 401，前端未处理 403 跳转 2026-07-17 20:46:05 +08:00
QihuAI Design e2369b4915 fix(market): 强化场景分类器解析兜底，避免合法 id 误判为 None 2026-07-17 15:44:58 +08:00
QihuAI Design dc3077b5ae fix(market): 强化场景分类器解析兜底，避免合法 id 误判为 None 2026-07-17 15:37:35 +08:00
QihuAI Design fe051bd9f3 feat(market): 采用元宝岗位/职能分类(14类)替代人群场景 + AI验证期自动归类 2026-07-17 15:22:57 +08:00
QihuAI Design 9bcf15099f feat(market): 技能/MCP 分类改为面向用户的业务场景(人群->场景)，AI验证期按场景归类 2026-07-17 14:55:21 +08:00
QihuAI Design 6f3fb400a4 feat(market): skills/mcp 能力分类 + AI验证期自动识别 + 导入自动入座 2026-07-17 12:09:42 +08:00
QihuAI Design 2ae5d9f9b5 fix(skills): 修复导入技能时 SKILL 内容丢失导致无法正常工作 
- 前端 handleSubmit/handleCreateApp 发送 skillsContent；handleHubImport 对 skill 把目录 URL 作为 download_url
- 后端 upload_app 对 skill 类型写入 skill_content（手动粘贴或 Hub 抓取）
- 新增 _fetch_skill_content 按目录 URL 抓取真实 SKILL.md 回填（best-effort，仅接受有效 markdown）
- 清理 50 条空壳 skill 记录（skill_content 为空，不可恢复）
- 经 E2E 验证：手动粘贴/Hub 抓取/MCP 重导三条路径均能正确落库
 2026-07-17 10:46:47 +08:00
QihuAI Design 47d38ca173 fix(MCP): 修复导入MCP时传输代码丢失导致无法连接的问题 
- 前端 MarketPage 提交时随 download_url 发送粘贴的 MCP 代码(handleSubmit+handleCreateApp)
- 后端新增 parse_mcp_config 解析标准 JSON 配置, 提取 url/headers/transport
- upload_app 与 _sync 使用解析器落库 mcp_servers 并自动连通性测试
- _test_mcp_server 连接测试携带 headers 鉴权头
- 优化 MCP 代码输入框占位符为真实配置格式
 2026-07-17 09:43:43 +08:00
QihuAI Design 24ed907ba5 feat: 实现MCP工具调用链路(streamable_http) - chat中MCP作为function calling真实调用tools/call 2026-07-16 20:59:42 +08:00
QihuAI Design ab90ac9473 fix: MCP后台删除/禁用同步清理market_apps源头,避免被_sync复活 2026-07-16 20:09:16 +08:00
QihuAI Design 6331e84185 feat: MCP streamable_http connection test + auto-test on import 2026-07-16 18:38:10 +08:00
QihuAI Design feb9865b00 fix: sync MarketApp MCP records to admin MCP Client management 2026-07-16 18:12:07 +08:00
QihuAI Design c9b5f964be feat(frontend): per-platform Streamable HTTP input for MCP Hub import 2026-07-16 17:36:58 +08:00
QihuAI Design e856f186be ui(mcp-hub): MCP导入弹窗复用 skills 优化方案 
两个问题：
1. 标题"导入Hub - MCP"偏左未居中 — .market-modal-header h2
   加 flex:1 + text-align:center
2. 说明textarea 与 MCP传输代码 框紧挨着无分隔 —
   .hub-code-section 加 margin-top: var(--space-xl)
 2026-07-16 16:39:12 +08:00
QihuAI Design e95fec0c1b ui(admin): 修复后台侧边栏 logo 区域未垂直居中 
.admin-sidebar-header 原 align-items: baseline + height: var(--header-height) + padding: 0
导致 logo 紧贴顶部边线。

修复：
- align-items: baseline → center
- padding: 0 var(--space-lg) → var(--space-md) var(--space-lg)
- height → min-height
- justify-content: center (水平居中)
- logo/subtitle 加 line-height: 1 + display: flex align-items: center
 2026-07-16 16:30:57 +08:00
QihuAI Design dc577eb0f0 feat(chat): 增强AI回复渲染 — 代码高亮/KaTeX数学/删除线/URL自动链接 
新增渲染能力：
1. highlight.js 代码语法高亮 + 复制按钮 (hover显示)
2. KaTeX 数学公式渲染 ($$...$$块级 + $...$行内)
3. 删除线 ~~text~~ → <del>
4. 裸URL自动转可点击链接

依赖: npm install highlight.js katex mermaid
 2026-07-16 16:25:41 +08:00
QihuAI Design 8486a2a0e5 ui(chat): MarkdownContent 支持表格渲染 
AI 聊天回复中常出现 Markdown 表格语法 (| h1 | h2 | + |---|---| )，
但 MarkdownContent 仅支持 headers/lists/code，未渲染表格，
显示为原始 | 分隔文本。

修复：
1. ChatPage.tsx MarkdownContent 新增表格解析步骤（步骤 2.7）
   - 匹配 | header |
|---|---| 的多行表格块
   - 解析对齐方式 (:---, :---:, ---:)
   - 生成 <table><thead><tbody> HTML
2. 步骤 10 恢复占位符，步骤 11 解包 <table> 不被 <p> 包裹
3. ChatPage.css 新增 .md-table 样式
   - 蓝色渐变表头 + 斑马纹 + hover 高亮
   - 用户消息气泡内深色适配
 2026-07-16 16:15:29 +08:00
QihuAI Design 845355e4e7 fix(timezone): 容器时区统一为 Asia/Shanghai，DB 历史 UTC 时间批量 +8h 修正 
根因：容器 TZ 为空（默认 UTC），Python datetime.now() 返回 UTC 写入
MySQL datetime 列时无时区转换，导致存储值被当成北京时间显示（偏 8h）。

修复：
1. run.sh 加 export TZ=Asia/Shanghai，新写入的时间即为北京时
2. 批量 UPDATE 所有 datetime 列 + INTERVAL 8 HOUR（105 表 216 列）
3. market_apps 等 59 表的 updated_at 因 ON UPDATE 触发器被重置，
   改为 = created_at（用户未实际编辑过）

后续：新写入的数据天然为北京时；旧数据已对齐。
 2026-07-16 16:07:59 +08:00
QihuAI Design 4d27dd3429 ui(import-hub): 优化 skills.sh 卡片布局 
- skills.sh 卡片改为列布局：
  顶部：图标+名称+URL（左侧）+ 访问按钮（右上）
  中部：URL 输入框（全宽）
  底部：检测名称预览 + 导入按钮（右下）
- 加大"说明"与平台卡片的间距（margin-top: space-xl）
- 导入按钮与名称预览在右侧同一行，间距更协调
 2026-07-16 16:00:35 +08:00
QihuAI Design 0e6f1931e1 fix(skills-admin): market 项加 publish_records 字段，列表"已发布"标识正确显示 
修复顶部卡片(已发布=50)与列表行(市场=未发布)不一致问题：
列表行 isPublished 仅看 skill.publish_records[]，
market_apps 项无该字段故一直显示"未发布"。
改为 market_app_to_skill_dict 中按 status 注入 publish_records。
 2026-07-16 15:46:43 +08:00