ed/manual_slop
Private
Public Access
0
0
Fork 0
Code Activity

docs(readme): add Subsystem Index, update tool count to 45, expand Tech Stack, link all 8 current guides

Browse Source
This commit is contained in:
Edward R. Gonzalez
2026-06-02 19:30:26 -04:00
parent 4f125241dd
commit 26938d4ad5
1 changed files with 55 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files
Readme.md
+55 -10
View File
@@ -6,7 +6,7 @@ A high-density GUI orchestrator for local LLM-driven coding sessions. Manual Slo
**Design Philosophy**: Full manual control over vendor API metrics, agent capabilities, and context memory usage. High information density, tactile interactions, and explicit confirmation for destructive actions.
**Tech Stack**: Python 3.11+, Dear PyGui / ImGui Bundle, FastAPI, Uvicorn, tree-sitter
**Tech Stack**: Python 3.11+, ImGui Bundle (Dear ImGui + imgui-node-editor + imgui_markdown + ImGuiColorTextEdit), FastAPI, Uvicorn, tree-sitter (Python, C, C++), chromadb (RAG), pywin32 (Windows window frame), psutil (telemetry), pydantic, dolt (Beads)
**Providers**: Gemini API, Anthropic API, DeepSeek, Gemini CLI (headless), MiniMax
**Platform**: Windows (PowerShell) — single developer, local use
@@ -35,13 +35,18 @@ Hierarchical task decomposition with specialized models and strict token firewal
- **Three Dialog Types**: ConfirmDialog (scripts), MMAApprovalDialog (steps), MMASpawnApprovalDialog (workers)
- **Editable Payloads**: Review, modify, or reject any AI-generated content before execution
### 26 MCP Tools with Sandboxing
### 45 MCP Tools with Sandboxing
Three-layer security model: Allowlist Construction → Path Validation → Resolution Gate
- **File I/O**: read, list, search, slice, edit, tree
- **AST-Based (Python)**: skeleton, outline, definition, signature, class summary, docstring
- **Analysis**: summary, git diff, find usages, imports, syntax check, hierarchy
- **Network**: web search, URL fetch
- **AST-Based (Python)**: skeleton, outline, definition, signature, class summary, docstring, var declaration, hierarchy, imports, syntax check, find usages
- **AST-Based (C/C++)**: tree-sitter powered skeleton, outline, definition, signature, and surgical update tools for C and C++
- **File Editing**: surgical string match (`edit_file`) preserving indentation and line endings
- **Analysis**: summary, git diff, find usages, imports, syntax check, hierarchy, derive code path
- **Network**: web search, URL fetch (dependency-free, stdlib only)
- **Runtime**: UI performance metrics
- **Beads**: bd_create, bd_list, bd_ready, bd_update for Dolt-backed issue tracking
See [docs/guide_tools.md](./docs/guide_tools.md) for the full inventory.
### Parallel Tool Execution
Multiple independent tool calls within a single AI turn execute concurrently via `asyncio.gather`, significantly reducing latency.
@@ -69,11 +74,46 @@ The **MMA (Multi-Model Agent)** system decomposes epics into tracks, tracks into
| Guide | Scope |
|---|---|
| [Readme](./docs/Readme.md) | Documentation index, GUI panel reference, configuration files, environment variables |
| [Architecture](./docs/guide_architecture.md) | Threading model, event system, AI client multi-provider architecture, HITL mechanism, comms logging |
| [Tools & IPC](./docs/guide_tools.md) | MCP Bridge 3-layer security, 26 tool inventory, Hook API endpoints, ApiHookClient reference, shell runner |
| [MMA Orchestration](./docs/guide_mma.md) | 4-tier hierarchy, Ticket/Track data structures, DAG engine, ConductorEngine, worker lifecycle, abort propagation |
| [Simulations](./docs/guide_simulations.md) | `live_gui` fixture, Puppeteer pattern, mock provider, visual verification, ASTParser / summarizer |
| [Meta-Boundary](./docs/guide_meta_boundary.md) | Application vs Meta-Tooling domains, inter-domain bridges, safety model separation |
| [Architecture](./docs/guide_architecture.md) | Threading model, event system, AI client multi-provider architecture (Gemini, Anthropic, DeepSeek, Gemini CLI, MiniMax), HITL mechanism, comms logging, RAG integration, Tier 4 patch flow |
| [Tools & IPC](./docs/guide_tools.md) | MCP Bridge 3-layer security, 45-tool inventory, Hook API endpoints, ApiHookClient reference, shell runner, Beads tools |
| [MMA Orchestration](./docs/guide_mma.md) | 4-tier hierarchy, Ticket/Track/WorkerContext data structures, DAG engine, ConductorEngine, worker lifecycle, persona application, abort propagation |
| [Simulations](./docs/guide_simulations.md) | `live_gui` fixture, Puppeteer pattern, mock provider, visual verification, test areas by subsystem, headless service |
| [Context Curation](./docs/guide_context_curation.md) | AST masking, fuzzy anchor slices, structural file editor, view presets, history snapshotting |
| [Shaders & Window](./docs/guide_shaders_and_window.md) | Hybrid shader injection, custom window frame, NERV theme effects |
| [Meta-Boundary](./docs/guide_meta_boundary.md) | Application vs Meta-Tooling domains, inter-domain bridges, cross-tool abstractions |
---
## Subsystem Index
| Subsystem | Guide | Primary Module(s) |
|---|---|---|
| Multi-provider LLM client | [Architecture](./docs/guide_architecture.md#ai-client-multi-provider-architecture) | `src/ai_client.py` |
| 4-Tier MMA orchestration | [MMA](./docs/guide_mma.md) | `src/multi_agent_conductor.py`, `src/dag_engine.py` |
| DAG engine & ticket lifecycle | [MMA](./docs/guide_mma.md#dag-engine-dag_enginepy) | `src/dag_engine.py` |
| MCP tools & Hook API | [Tools & IPC](./docs/guide_tools.md) | `src/mcp_client.py`, `src/api_hooks.py` |
| Execution Clutch (HITL) | [Architecture](./docs/guide_architecture.md#the-execution-clutch-human-in-the-loop) | `src/app_controller.py` |
| Context composition & aggregation | [Context Curation](./docs/guide_context_curation.md) | `src/aggregate.py`, `src/file_cache.py` |
| AST inspection & slicing | [Context Curation](./docs/guide_context_curation.md#granular-ast-control) | `src/file_cache.py`, `src/fuzzy_anchor.py` |
| Personas (unified profiles) | *See [guide_mma.md](./docs/guide_mma.md#persona-application); dedicated guide pending* | `src/personas.py` |
| Tool bias engine | *See [guide_tools.md](./docs/guide_tools.md); dedicated guide pending* | `src/tool_bias.py` |
| RAG (Retrieval-Augmented Generation) | *See [guide_architecture.md](./docs/guide_architecture.md#rag-integration); dedicated guide pending* | `src/rag_engine.py` |
| Beads mode (Dolt issue tracking) | *See [guide_tools.md](./docs/guide_tools.md#beads-tools); dedicated guide pending* | `src/beads_client.py` |
| Hot reload (state-preserving) | *Dedicated guide pending* | `src/hot_reloader.py` |
| Discussion metrics & compression | [Architecture](./docs/guide_architecture.md#discussion-compression) | `src/ai_client.py` |
| Test infrastructure & simulations | [Simulations](./docs/guide_simulations.md) | `tests/conftest.py`, `simulation/` |
| Headless service (FastAPI) | [Simulations](./docs/guide_simulations.md#headless-service-tests) | `src/api_hooks.py` |
| NERV theme & visual effects | [Shaders & Window](./docs/guide_shaders_and_window.md#4-nerv-theme-effects) | `src/theme_nerv.py`, `src/theme_nerv_fx.py` |
| Custom window frame | [Shaders & Window](./docs/guide_shaders_and_window.md#2-custom-window-frame-strategy) | `src/gui_2.py` |
| Workspace profiles (docking layouts) | *Dedicated guide pending* | `src/workspace_manager.py` |
| History (undo/redo) | [Context Curation](./docs/guide_context_curation.md#context-snapshotting-per-take) | `src/history.py` |
| External MCP integration | [Tools & IPC](./docs/guide_tools.md#external-mcp-integration) | `src/mcp_client.py` |
| Telemetry & performance monitoring | [Architecture](./docs/guide_architecture.md#telemetry--auditing) | `src/performance_monitor.py` |
| Session logging | [Tools & IPC](./docs/guide_tools.md#session-logging) | `src/session_logger.py` |
| MMA dashboard & node editor | [MMA](./docs/guide_mma.md) | `src/gui_2.py:_render_mma_dashboard` |
| Cross-tool abstractions (conductor) | [Meta-Boundary](./docs/guide_meta_boundary.md#the-cross-tool-abstractions) | `conductor/` |
Subsystems marked "dedicated guide pending" are slated for dedicated `docs/guide_*.md` files in upcoming docs work. For now, their details live inline in the guides listed under [Documentation](#documentation) above.
---
@@ -105,8 +145,13 @@ api_key = "YOUR_KEY"
[deepseek]
api_key = "YOUR_KEY"
[minimax]
api_key = "YOUR_KEY"
```
Each provider's key is loaded by the corresponding `_ensure_<provider>_client()` in `src/ai_client.py`. The `credentials.toml` is **blacklisted** by the MCP allowlist — AI tools cannot read it under any circumstance.
### Running
```powershell