mirror of https://github.com/val1813/kwcode.git synced 2026-09-03 06:34:30 +08:00

Files

Val-sss 4856d3a617 docs: mark TODO items 1-3 as completed in STATUS.md

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

2026-05-06 18:04:00 +08:00

9.0 KiB

Raw Blame History

KWCode Project Status

Path: D:\program\codeagent2604\kwcode GitHub: https://github.com/val1813/kwcode Started: 2026-04-26 Goal: Local-model coding agent — maximize task completion rate via deterministic expert pipeline

Current: v1.5.0 (2026-05-06)

451/451 tests green. Architecture upgrade: isolated search + cross-file contracts + PENCIL compression.

v1.5.0 — Isolated Search + Cross-File Contracts

Theory: WarpGrep (isolated search subagent) + CGM (graph-injected attention) + PENCIL (erase intermediate state) + SWE-ContextBench (context quality > model size)

SearchSubagent (experts/search_subagent.py)

Independent context window — search noise never enters Generator
Parallel file reads: ThreadPoolExecutor, 8 concurrent
Returns only precise {file, start_line, end_line, content}
Shadow TaskContext: Locator writes to shadow, main ctx stays clean

UpstreamManifest (core/upstream_manifest.py)

Deterministic AST extraction: Python ast module, regex fallback for others
Tracks: function signatures, constants, import dependencies
get_constraints_for_file() → injected into Generator prompt
check_consistency() → Verifier pre-check, catches arg count / constant mismatches
Zero LLM calls

PENCIL Compression + Contract Verification

task_compiler: _compact_subtask_result() keeps only signatures/constants/paths/test_status
orchestrator: locator step uses SearchSubagent, verifier pre-checks contracts
contract_violation error type triggers re-locate retry strategy
Generator prompt receives upstream_constraints + retry_hint

Code Quality (this release)

orchestrator.py run() split into 5 private methods (410→253 lines)
Full type annotations: Optional[DebugSubagent], Callable[[str,str],None]
all added to 7 core modules
pyproject.toml: license fixed, ruff + mypy configured
TUI: 30+ event icons added (contract_violation, ab_test, replay, etc.)
Server: /api/manifest endpoint, version 1.5.0

v1.4.0 — Multi-Language + TUI + IDE

Theory: XRAY MCP Server + OpenCode + CodeCompass

7-language AST (Python/JS/TS/Go/Rust/Java/C#)
ast-grep with QUERY_TEMPLATES (LLM never writes patterns)
FastAPI server (port 7355) + SSE streaming
Textual TUI (file tree + event log + input)
VSCode extension (thin client, all logic server-side)

v1.3.0 — EventBus + Error Strategy + Cognitive Gate

Theory: Dive into Claude Code + Wink + ARCS + SpecEyes + OPENDEV + Turn-Control

EventBus: append-only log, replay, wildcard listeners
ToolGateway: per-expert permissions, file cache with dirty tracking
Error strategy routing: 6 error types → different retry sequences
CognitiveGate: diminishing returns detection → auto-stop
GraduatedCompactor: 3-layer progressive context compression
Plan auto-trigger for hard tasks
Worktree isolation (git worktree / tempdir fallback)
Speculative Prefetch: background file pre-read
SearchRouter: intent-aware routing (arXiv/S2/GitHub/PyPI/Open-Meteo)
Wink self-repair: scope_creep / repetitive_fix / patch_miss / empty_output

v1.2.0 — RIG Project Map

Theory: RIG + FastCode + CodeCompass

export_rig(): full project index (exports/imports/routes/test coverage)
upstream_summary structured dict for multi-task context passing
ConsistencyChecker: deterministic frontend/backend API mismatch detection
Gate/Locator prompt explicitly guided to query rig.json

v1.1.0 — P0+P1+P2 Optimizations

Verifier structured output (_classify_error: 5 error types)
Circuit breakers (syntax 1x, import immediate, same-type 3x streak)
Gate confidence scoring (0.92/0.75/0.55)
Experience Replay (BM25 similar trajectory lookup)
Session continuity (SessionState, 5-turn KWCODE.md re-injection)
Locator minimal context (function boundaries, 60-line cap, gap markers)
Watchdog 300s timeout
Gate accuracy stats (/stats command)

v0.9.0 — DAG Compiler + Debug Subagent

TaskCompiler: DAG scheduler, ThreadPoolExecutor + Kahn topological sort
Debug Subagent: sys.settrace variable capture on failure
Prompt Optimizer: trajectory → experience rules → YAML system_prompt
Cross-Encoder search reranking

Core Pipeline (v0.5.0–v0.8.0)

Gate → 6 pipeline routes (locator_repair/codegen/refactor/doc/office/chat)
BM25+AST call graph two-phase location (zero LLM, milliseconds)
Generator: original from file, LLM only generates modified
Verifier: syntax check + pytest
3-stage retry + Reflection root cause analysis
5 deterministic tools (read_file/write_file/run_bash/list_dir/git)
KWCODE.md project rules + /plan + Checkpoint + DocReader
Model capability tiers (SMALL/MEDIUM/LARGE)
Expert flywheel (trajectory → pattern → backtest → AB test → production)
3-layer memory (PROJECT.md/EXPERT.md/PATTERN.md)
Office document generation (Excel/PPT/Word)
MCP Router, context compression, CJK BM25

Test Summary

Category	Count	Status
Core unit tests	38	PASS
Regression tests	173	PASS
P1 feature tests	33	PASS
P2 feature tests	21	PASS
Search refactor	19	PASS
Intent search	19	PASS
E2E real model	17	PASS
RIG modules	29	PASS
TaskCompiler	12	PASS
Multi-language	51	PASS
Server/TUI	16	PASS
SearchSubagent+Manifest	27	PASS
Total	451	All green

File Structure

kwcode/
├── pyproject.toml
├── README.md / README_zh.md
├── STATUS.md
└── kaiwu/
    ├── cli/
    │   ├── main.py              # REPL + EventBus rendering + spinner + summary
    │   ├── status_bar.py        # Status bar (4-tier adaptive)
    │   └── onboarding.py        # First-run onboarding
    ├── core/
    │   ├── event_bus.py         # Unified event bus (append-only + replay)
    │   ├── cognitive_gate.py    # Diminishing returns detection
    │   ├── wink.py              # Self-repair monitor
    │   ├── gate.py              # LLM task classification → expert routing
    │   ├── orchestrator.py      # Deterministic pipeline + error strategy routing
    │   ├── context.py           # TaskContext dataclass
    │   ├── task_compiler.py     # DAG scheduler + WorktreeManager
    │   ├── upstream_manifest.py # [v1.5] Cross-file contract tracking (zero LLM)
    │   ├── planner.py           # /plan mode + risk assessment
    │   ├── checkpoint.py        # File snapshot (git stash / file copy)
    │   ├── kwcode_md.py         # KWCODE.md segmented loading
    │   ├── model_capability.py  # Model tier detection (SMALL/MEDIUM/LARGE)
    │   ├── context_pruner.py    # Context compression + GraduatedCompactor
    │   ├── network.py           # Network detection + proxy config
    │   └── sysinfo.py           # System info + VRAM monitoring
    ├── experts/
    │   ├── locator.py           # BM25+graph location + DocReader + Prefetch
    │   ├── search_subagent.py   # [v1.5] Isolated search (independent context)
    │   ├── generator.py         # Code generation (original from file, LLM writes modified)
    │   ├── verifier.py          # Syntax + pytest + cross-file contract check
    │   ├── search_augmentor.py  # Search augmentation + BM25 rerank
    │   ├── consistency_checker.py # Frontend/backend API consistency (deterministic)
    │   ├── chat_expert.py       # Chat (search gating)
    │   └── office_handler.py    # Office document generation
    ├── search/                  # Intent-aware search routing
    ├── knowledge/               # PDF/Word/MD reader + CJK BM25
    ├── flywheel/                # Trajectory → pattern → generation → AB test
    ├── registry/                # Expert registry + .kwx packaging
    ├── notification/            # Flywheel notifications
    ├── stats/                   # Value tracking (SQLite)
    ├── memory/                  # 3-layer memory system
    ├── ast_engine/              # tree-sitter AST + call graph
    ├── server/                  # FastAPI + SSE (port 7355)
    ├── tui/                     # Textual TUI
    ├── mcp/                     # MCP Router
    ├── llm/                     # Ollama + llama.cpp backends
    ├── tools/                   # 5 deterministic tools + ToolGateway
    └── tests/                   # 451 tests

TODO

~~CLI refactor: split main.py (1861 lines) into cli/commands/~~ ✅ v1.5.0
~~Comments: unify to Chinese across all modules~~ ✅ v1.5.0
~~Expert-level EventBus emit (file reads, function locations, test results)~~ ✅ v1.5.0
SQLite cross-session queries
Full expert benchmark (12 presets)
pip publish to PyPI
install.ps1 / install.sh one-click install

Known Issues

qwen3-vl:8b outputs in thinking field, content empty (thinking extraction added)
Reasoning models slow on Gate (8x multiplier)
SearXNG requires Docker Desktop, degrades to DDG without it

9.0 KiB Raw Blame History Unescape Escape