Commit Graph

3 Commits

Author SHA1 Message Date
AirCoding
e383d5f6a7 fix: 主线 B3/B4 结构化工具调用与完成前验证
- 打通 Worker → WorkerManager → Provider 的 tools 传递链路,ProviderManager/adapter
  返回结构化 tool_calls 给 WorkerRuntime
- OpenAI-compatible/Anthropic adapter 发送工具 schema,并解析 provider 返回的
  tool_calls/tool_use;OpenAI 工具名使用 fs.write ↔ fs__write 双向映射
- 修复独立复审发现的 OpenAI 协议隐患:assistant tool_use blocks 必须转换为
  assistant.tool_calls,后续 role=tool 消息的 tool_call_id 必须匹配前一轮
  tool_calls[].id;不再把 tool_use JSON 字符串化为普通文本
- ExecutorRole 优先消费原生 tool_calls,回灌 canonical tool_result block;移除
  fs.write(...)/shell.run(...) 函数调用正则解析,只保留严格 JSON tool_call
  fallback 与 filename code block 兼容
- DONE 前执行 verification-before-completion:任务要求 build/compile/run/test/编译/
  运行/测试时必须实际 shell.run 验证,失败不 checkpoint、不返回 completed
- fs.write 覆盖已有文件也强制 read-before-write,补齐 Claude Code 文件状态纪律
- 新增 packages/workers/test/executor-role.test.ts 行为测试:原生 tool_calls 执行、
  verification 失败不得 completed

真实验收:
- TSC=0
- bun test packages/workers/test/executor-role.test.ts: 2 pass / 0 fail
- OpenAI converter 探针确认 assistant.tool_calls 与 role=tool 的 tool_call_id 匹配
- 真实 GLM Worker C++ 编译运行任务通过,worker verification 记录实际命令:
  c++ hello.cpp -o /tmp/aircoding-verify && /tmp/aircoding-verify

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-06-08 15:01:16 +08:00
AirCoding
ea7cf427dd fix: tsc 0 errors + depcruise 0 violations + all GA blockers closed
Changes (37 files, +1159/-587):
- tsconfig: moduleResolution bundler + paths alias for bun:sqlite
- bun-sqlite.ts: type shim replacing stale declare module .d.ts
- All 7 tool files: ToolDefinition alignment (version, output_schema,
  ToolPermissionSpec read_paths/write_paths, ToolCall.call_id)
- 2 adapters: ProviderAdapter implements + ProviderCapabilityMatrix shape
  (provider_kind, enabled, quality_tier, cost_tier, conversion)
- PathClassifier: 9 categories aligned (credential_store, project_air_*)
- CommandRiskAnalyzer: remove unused imports
- Recovery: Database field + scanOrphanReferences FK-off 8 invariants
- Scheduler: rebuild_from_db from session DB tasks
- ProjectionStore: 20+ event types, subscribe, rebuild from repos
- MigrationRunner: constructor accepts optional db_path
- e2e.ts: replaced hardcoded  with 14 real test/check gates
- wiring.ts: eventIngestor.ingest (durable path, INV-2)
- init.ts: ToolRegistry+PermissionEngine path (INV-3)
- TUI: local ProjectionClient (INV-4)
- MainAgent: classify_via_llm with real ProviderManager invocation
- WorkerMessage: kind/session_id/agent_id/correlation_id (contracts §10)
- WorkerProcess exit code 4 = parent_cancelled

Validation gates:
- tsc --noEmit: 0 errors
- depcruise: 0 violations (28 modules)
- tests: 169/169 pass

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-04 11:43:19 +08:00
AirCoding
a773bac28c P0-P8: Full V1.0.0 Alpha implementation + audit reports
Implements 123 tasks across 9 phases (T-001..T-809) totaling 146 source files.

Monorepo (P0):
- 7-package Bun + Turborepo + TypeScript monorepo
- dependency-cruiser enforcing 7 forbidden edges + 5 deep-import rules

Contracts (P0):
- 16 type files (ids/error/event/runtime/ipc/task/worker-result/tool/artifact/evidence/project/provider/permission/ui/capability/platform)

Storage & Events (P1):
- DatabaseManager + MigrationRunner (19 tables, 22 indexes, 5 schema_meta seeds)
- 16 repositories (Repository<T,I,U> pattern, INV-1 status columns via EventStore.project only)
- EventSchemaRegistry (54 durable + 7 ephemeral), EventStore, EventBus, EventIngestor
- Project/Session/Artifact/Evidence stores + 8-step Recovery

Tools & Permission (P2):
- PathClassifier (8 categories), CommandRiskAnalyzer (10 categories), SecretRedactor
- PermissionEngine 6-layer evaluation (capability→profile→task_scope→risk→credential→user_prompt)
- ToolRegistry with 20+ tools across fs/shell/git/project/artifact/context/permission/doctor
- CapabilityManifestValidator + CapabilityRegistry

LLM & Context (P3):
- ModelConfigLoader, CapabilityMatrix, AnthropicCanonicalConverter
- AnthropicAdapter + OpenAICompatibleAdapter
- ProviderManager facade
- PromptLayerLoader (L0/L1/L3/L5), CompactionPolicy, ContextAssembler

Worker IPC & Scheduler (P4):
- WorkerProtocol (NDJSON), WorkerProcess (exit codes 0-5), WorkerManager (spawn/handshake)
- WorkerRuntime (INV-3: IPC only, no direct fs/shell/SQLite)
- 5 worker roles (Executor/Reviewer/Debugger/Compactor/ExperienceMiner)
- TaskGraph, WavePlanner, RetryPlanner, AgentMonitor, WorkspaceManager
- Scheduler (state machine), 8-step Recovery

C++ Toolchain (P5):
- DiagnosticParser, CppProjectDetector, CMakeConfigurator, CppBuilder
- CppTestRunner, CppcheckRunner, ClangdClient
- CppToolRegistrar + capability manifest

Projection & TUI (P6):
- ProjectionStore (hydrate/apply/snapshot/subscribe)
- TuiApp + 8 components (Session/Task/Agent/Tool/Diff/Evidence/Permission/Blocker/Hud)
- ProjectionClient in-process ref

Agents & Knowledge (P7):
- MainAgent, ArchitectureDesigner
- DebugKnowledgeStore + LearnedMemoryStore (single-writer, outbox model)
- Role integration wiring

CLI & Doctor & Release (P8):
- Logger + DeveloperLogEncryptor (AES-256-GCM)
- DoctorService (self_bootstrap first)
- RuntimeApp + ServiceRegistry
- 11 CLI commands: run/init/doctor/provider/resume/compact/history/session/restore/e2e/release
- CliEntrypoint + air<TODO>

Audit (in AirPlan/docs/):
- Deepseek开发阶段审计.md (97 findings)
- Opus开发阶段审计.md (140+ findings, 18 P0 blockers)
- MiniMaxM3开发阶段审计.md (18 P0 blockers, focuses on executability)
- AirPlan/TODO.md (technical debt + 42 TODOs by phase)

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-02 19:19:55 +08:00