Commit Graph

5 Commits

Author SHA1 Message Date
Fam Zheng
c70fbc49f0 feat: auto-install Python deps from template pyproject.toml via uv
ExternalToolManager.discover() now accepts template root dir, detects
pyproject.toml and runs `uv sync` to create a venv. Tool invocation and
schema discovery inject the venv PATH/VIRTUAL_ENV so template tools can
import declared dependencies without manual installation.
2026-03-09 15:22:35 +00:00
Fam Zheng
fa800b1601 feat: step artifacts framework
- Add Artifact type to Step (name, path, artifact_type, description)
- step_done tool accepts optional artifacts parameter
- Save artifacts to step_artifacts DB table
- Display artifacts in frontend PlanSection (tag style)
- Show artifacts in step context for sub-agents and coordinator
- Add LLM client retry with exponential backoff
2026-03-09 12:01:29 +00:00
0a8eee0285 LLM call logging, plan persistence API, quote-to-feedback UX, requirement input improvements
- Add llm_call_log table and per-call timing/token tracking in agent loop
- New GET /workflows/{id}/plan endpoint to restore plan from snapshots on page load
- New GET /workflows/{id}/llm-calls endpoint + WS LlmCallLog broadcast
- Parse Usage from LLM API response (prompt_tokens, completion_tokens)
- Detailed mode toggle in execution log showing LLM call cards with phase/tokens/latency
- Quote-to-feedback: hover quote buttons on plan steps and log entries, multi-quote chips in comment input
- Requirement input: larger textarea, multi-line display with pre-wrap and scroll

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-02 09:16:51 +00:00
2df4e12d30 Agent loop state machine refactor, unified LLM interface, and UI improvements
- Rewrite agent loop as Planning→Executing(N)→Completed state machine with
  per-step context isolation to prevent token explosion
- Split tools and prompts by phase (planning vs execution)
- Add advance_step/save_memo tools for step transitions and cross-step memory
- Unify LLM interface: remove duplicate types, single chat_with_tools path
- Add UTF-8 safe truncation (truncate_str) to prevent panics on Chinese text
- Extract CreateForm component, add auto-scroll to execution log
- Add report generation with app access URL, non-blocking title generation
- Add timer system, file serving, app proxy, exec module
- Update Dockerfile with uv, deployment config

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-28 22:35:33 +00:00
7edbbee471 Tori: AI agent workflow manager - initial implementation
Rust (Axum) + Vue 3 + SQLite. Features:
- Project CRUD REST API with proper error handling
- Per-project agent loop (mpsc + broadcast channels)
- LLM-driven plan generation and replan on user feedback
- SSH command execution with status streaming
- WebSocket real-time updates to frontend
- Four-zone UI: requirement, plan (left), execution (right), comment

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-28 10:36:50 +00:00