aiagent

admin/aiagent

Fork 0

Commit Graph

Author	SHA1	Message	Date
renjianbo	495eafcd78	feat: virtual company M2 control + tier-3/4 capabilities + per-dept session fix - M2-a/b/c: stop/pause/resume/skip dept, plan/rework approval gates, budget & timeout circuit breakers, per-dept cancel and on-demand rework - tier-3: batched event persistence (_EventBuffer), project/dept concurrency semaphores, company_ws event streaming - tier-4: cross-dept deliverable handoff, CEO memory feedback loop, per-dept model override, one-click Markdown report export (RFC5987) - fix: per-department independent SQLAlchemy session in parallel waves (shared Session race across asyncio tasks in company_orchestrator) - fix: rename process_open_fds gauge to app_process_open_fds (collides with prometheus_client ProcessCollector on Linux) - fix: dept role resolution ladder, real token usage & cost tracking, deliverable file capture (mtime scan of dept workspace) - tests: test_company_orchestrator.py 22 cases with mocked LLM - frontend: CompanyControlRoom, companyExecution store, EChart, dept model config dialog, ws proxy, build/typecheck decoupling - docs: virtual company design/usage docs, M2 control plan, deepseek4pro handover docs Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>	2026-07-26 18:16:39 +08:00
renjianbo	10ee7ee625	refactor: rename platform from 低代码智能体平台 to 天工智能体平台 The platform has evolved from a low-code workflow engine to an autonomous agent platform with ReAct runtime, multi-agent marketplace, persistent memory, multimodal tools, and multi-channel integration. "天工" (Tiangong) draws from 《天工开物》- the wonders of nature and human ingenuity, reflecting the platform's purpose: empowering users to create and orchestrate AI agents as masterfully as nature creates all things. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>	2026-05-08 00:56:00 +08:00
renjianbo	eabf90c496	feat: add AI学习助手 agent (KG+RAG ideal) and renshenguo feishu bot - Add AI学习助手 agent creation script with all 39 tools, 3-layer KG+RAG memory - Add renshenguo (人参果) feishu bot integration (app_service + ws_handler) - Register renshenguo WS client in main.py startup - Add RENSHENGUO_APP_ID / RENSHENGUO_APP_SECRET / RENSHENGUO_AGENT_ID config - Reorganize docs from root into docs/ subdirectories - Move startup scripts to scripts/startup/ - Various backend optimizations and tool improvements Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>	2026-05-06 01:37:13 +08:00

Author

SHA1

Message

Date

renjianbo

495eafcd78

feat: virtual company M2 control + tier-3/4 capabilities + per-dept session fix

- M2-a/b/c: stop/pause/resume/skip dept, plan/rework approval gates,
  budget & timeout circuit breakers, per-dept cancel and on-demand rework
- tier-3: batched event persistence (_EventBuffer), project/dept
  concurrency semaphores, company_ws event streaming
- tier-4: cross-dept deliverable handoff, CEO memory feedback loop,
  per-dept model override, one-click Markdown report export (RFC5987)
- fix: per-department independent SQLAlchemy session in parallel waves
  (shared Session race across asyncio tasks in company_orchestrator)
- fix: rename process_open_fds gauge to app_process_open_fds
  (collides with prometheus_client ProcessCollector on Linux)
- fix: dept role resolution ladder, real token usage & cost tracking,
  deliverable file capture (mtime scan of dept workspace)
- tests: test_company_orchestrator.py 22 cases with mocked LLM
- frontend: CompanyControlRoom, companyExecution store, EChart,
  dept model config dialog, ws proxy, build/typecheck decoupling
- docs: virtual company design/usage docs, M2 control plan,
  deepseek4pro handover docs

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

2026-07-26 18:16:39 +08:00

renjianbo

10ee7ee625

refactor: rename platform from 低代码智能体平台 to 天工智能体平台

The platform has evolved from a low-code workflow engine to an autonomous
agent platform with ReAct runtime, multi-agent marketplace, persistent
memory, multimodal tools, and multi-channel integration.

"天工" (Tiangong) draws from 《天工开物》- the wonders of nature and human
ingenuity, reflecting the platform's purpose: empowering users to create
and orchestrate AI agents as masterfully as nature creates all things.

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

2026-05-08 00:56:00 +08:00

renjianbo

eabf90c496

feat: add AI学习助手 agent (KG+RAG ideal) and renshenguo feishu bot

- Add AI学习助手 agent creation script with all 39 tools, 3-layer KG+RAG memory
- Add renshenguo (人参果) feishu bot integration (app_service + ws_handler)
- Register renshenguo WS client in main.py startup
- Add RENSHENGUO_APP_ID / RENSHENGUO_APP_SECRET / RENSHENGUO_AGENT_ID config
- Reorganize docs from root into docs/ subdirectories
- Move startup scripts to scripts/startup/
- Various backend optimizations and tool improvements

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

2026-05-06 01:37:13 +08:00

3 Commits