18 lines
8.6 KiB
JSON
18 lines
8.6 KiB
JSON
{
|
|
"C:\\projects\\manual_slop\\src\\ai_client.py": {
|
|
"hash": "db4b3aad82599499d7796860757e229d2d412c5ccb3e821ddaee68ca0d3ad5d3",
|
|
"summary": "This Python module serves as a unified client interface for multiple Large Language Model (LLM) providers, abstracting away provider-specific differences in tool handling, history management, and caching. It includes specialized logic for Anthropic to manage token limits and for Gemini to inject initial context efficiently.\n\n* **Multi-Provider Abstraction:** Provides a single interface for interacting with LLMs from Anthropic, Gemini, DeepSeek, and Minimax.\n* **Provider-Specific Optimization:** Implements tailored strategies for managing token limits (Anthropic) and context injection (Gemini).\n* **Tooling and Bias Management:** Supports setting agent tools, tool presets, and bias profiles to influence LLM behavior.\n* **Communication Logging:** Tracks and logs communication events with LLM providers.\n* **Configuration and State Management:** Manages global generation parameters, credentials, and session state.\n\n**Outline:**\n**Python** \u2014 2501 lines\nimports: __future__, anthropic, asyncio, collections, datetime, difflib, google, hashlib, json, openai, os, pathlib, requests, src, sys, threading, time, tomllib, typing\nconstants: _GEMINI_CACHE_TTL, _BIAS_ENGINE, MAX_TOOL_ROUNDS, _MAX_TOOL_OUTPUT_BYTES, _ANTHROPIC_CHUNK_SIZE, _SYSTEM_PROMPT, COMMS_CLAMP_CHARS, TOOL_NAME, _CACHED_ANTHROPIC_TOOLS, _DIFF_LINE_THRESHOLD, _CACHED_DEEPSEEK_TOOLS, _CHARS_PER_TOKEN, _ANTHROPIC_MAX_PROMPT_TOKENS, _GEMINI_MAX_INPUT_TOKENS, _FILE_REFRESH_MARKER\nclass ProviderError: __init__, ui_message\nfunctions: set_model_params, get_history_trunc_limit, set_history_trunc_limit, get_current_tier, set_current_tier, set_custom_system_prompt, set_base_system_prompt, set_use_default_base_prompt, set_project_context_marker, _get_context_marker, _get_combined_system_prompt, get_combined_system_prompt, _append_comms, get_comms_log, clear_comms_log, get_credentials_path, _load_credentials, _classify_anthropic_error, _classify_gemini_error, _classify_deepseek_error, _classify_minimax_error, set_provider, get_provider, cleanup, reset_session, get_gemini_cache_stats, list_models, _list_gemini_cli_models, _list_gemini_models, _list_anthropic_models, _list_deepseek_models, _list_minimax_models, set_agent_tools, set_tool_preset, set_bias_profile, get_bias_profile, _build_anthropic_tools, _get_anthropic_tools, _gemini_tool_declaration, _execute_tool_calls_concurrently, _execute_single_tool_call_async, _run_script, _truncate_tool_output, _reread_file_items, _build_file_context_text, _build_file_diff_text, _build_deepseek_tools, _get_deepseek_tools, _content_block_to_dict, _ensure_gemini_client, _get_gemini_history_list, _send_gemini, _send_gemini_cli, _estimate_message_tokens, _invalidate_token_estimate, _estimate_prompt_tokens, _strip_stale_file_refreshes, _trim_anthropic_history, _ensure_anthropic_client, _chunk_text, _build_chunked_context_blocks, _strip_cache_controls, _add_history_cache_breakpoint, _repair_anthropic_history, _send_anthropic, _ensure_deepseek_client, _ensure_minimax_client, _repair_deepseek_history, _send_deepseek, _send_minimax, run_tier4_analysis, run_tier4_patch_callback, run_tier4_patch_generation, get_token_stats, send, _add_bleed_derived, get_history_bleed_stats, run_subagent_summarization"
|
|
},
|
|
"C:\\projects\\manual_slop\\conductor\\workflow.md": {
|
|
"hash": "ac3f4c0b807ce88bbbfdbd33b4d0888d4d5f97abca5642c2d5a3d9f2c1bc9fa5",
|
|
"summary": "This document outlines the mandatory workflow for the Conductor project, emphasizing strict adherence to code style, a test-driven development process with delegated implementation, and atomic, well-documented commits. Key takeaways include the critical importance of 1-space indentation for Python, the use of specific MCP tools to avoid indentation destruction, and a multi-phase task execution involving research, failing tests, implementation, refactoring, and thorough documentation via Git notes.\n\n**Outline:**\n**Markdown** \u2014 389 lines\nheadings:\n Project Workflow\n Session Start Checklist (MANDATORY)\n Code Style (MANDATORY - Python)\n CRITICAL: Native Edit Tool Destroys Indentation\n Guiding Principles\n Task Workflow\n Standard Task Workflow\n Phase Completion Verification and Checkpointing Protocol\n Verification via API Hooks\n Quality Gates\n Development Commands\n Setup\n Example: Commands to set up the development environment (e.g., install dependencies, configure database)\n e.g., for a Node.js project: npm install\n e.g., for a Go project: go mod tidy\n Daily Development\n Example: Commands for common daily tasks (e.g., start dev server, run tests, lint, format)\n e.g., for a Node.js project: npm run dev, npm test, npm run lint\n e.g., for a Go project: go run main.go, go test ./..., go fmt ./...\n Before Committing\n Example: Commands to run all pre-commit checks (e.g., format, lint, type check, run tests)\n e.g., for a Node.js project: npm run check\n e.g., for a Go project: make check (if a Makefile exists)\n Testing Requirements\n Structural Testing Contract\n Unit Testing\n Integration Testing\n Mobile Testing\n Code Review Process\n Self-Review Checklist\n Commit Guidelines\n Message Format\n Types\n Examples\n Definition of Done\n Conductor Token Firewalling & Model Switching Strategy\n 1. Active Model Switching (Simulating the 4 Tiers)\n 2. Context Management and Token Firewalling\n 3. Phase Checkpoints (The Final Defense)"
|
|
},
|
|
"C:\\projects\\manual_slop\\src\\models.py": {
|
|
"hash": "6e097e6a78ff02e3050212f3021761ebfe2aa9ce82b7074656842b394453ec90",
|
|
"summary": "This module defines the core data structures for the Manual Slop application, including tasks, tracks, and configuration, enabling project orchestration and persistence.\n\n* **Data Models:** Defines `Ticket`, `Track`, `WorkerContext`, `Metadata`, `TrackState`, `FileItem`, `Preset`, `Tool`, `ToolPreset`, `BiasProfile`, `Persona`, `MCPServerConfig`, `MCPConfiguration`, `VectorStoreConfig`, `RAGConfig`, and `WorkspaceProfile` as dataclasses.\n* **Serialization:** Implements `to_dict` and `from_dict` methods for all dataclasses to support TOML/JSON persistence.\n* **Configuration Management:** Provides functions `load_config`, `save_config`, and `parse_history_entries` for managing application settings and historical data.\n* **Tool Definitions:** Lists available `AGENT_TOOL_NAMES` and categorizes them in `DEFAULT_TOOL_CATEGORIES`.\n\n**Outline:**\n**Python** \u2014 704 lines\nimports: __future__, dataclasses, datetime, json, os, pathlib, re, src, sys, tomli_w, tomllib, typing\nconstants: CONFIG_PATH, AGENT_TOOL_NAMES, DEFAULT_TOOL_CATEGORIES\nclass ThinkingSegment: to_dict, from_dict\nclass Ticket: mark_blocked, mark_manual_block, clear_manual_block, mark_complete, get, to_dict, from_dict\nclass Track: get_executable_tickets, to_dict, from_dict\nclass WorkerContext\nclass Metadata: to_dict, from_dict\nclass TrackState: to_dict, from_dict\nclass FileItem: to_dict, from_dict\nclass Preset: to_dict, from_dict\nclass Tool: to_dict, from_dict\nclass ToolPreset: to_dict, from_dict\nclass BiasProfile: to_dict, from_dict\nclass Persona: provider, model, temperature, top_p, max_output_tokens, to_dict, from_dict\nclass MCPServerConfig: to_dict, from_dict\nclass MCPConfiguration: to_dict, from_dict\nclass VectorStoreConfig: to_dict, from_dict\nclass RAGConfig: to_dict, from_dict\nclass WorkspaceProfile: to_dict, from_dict\nfunctions: _clean_nones, load_config, save_config, parse_history_entries, load_mcp_config"
|
|
},
|
|
"C:\\projects\\manual_slop\\tests\\test_saved_presets_sim.py": {
|
|
"hash": "4b059b49282ecaede5171f4e0ad0ca789d00f9794b4c8e7bea1b95b7cd66c3b4",
|
|
"summary": "This Python file contains tests for the preset management functionality of the `manual_slop` application, specifically focusing on how global and project-specific presets are loaded, applied, and managed through a GUI interface.\n\n* **Environment Setup:** Initializes a temporary workspace with necessary configuration files for testing.\n* **Preset Switching:** Tests the ability to apply global and project presets, verifying that project-specific presets can override global ones and that selecting \"None\" correctly clears the active preset.\n* **Preset Manager Modal:** Simulates interactions with a modal to create and delete presets, verifying that changes are correctly persisted to the respective TOML files.\n\n**Outline:**\n**Python** \u2014 167 lines\nimports: json, os, pathlib, pytest, shutil, src, time, tomli_w, tomllib\nfunctions: test_env_setup, test_preset_switching, test_preset_manager_modal"
|
|
}
|
|
} |