Val-sss 8fd5275b2e feat: complete MoE framework — token budget, guardrails, observability, session continuity ...

P1: Token budget tracking (llm/llama_backend.py)
  - Auto-count input/output tokens per LLM call
  - BudgetExceededError when over limit
  - OpenAI API uses real usage data, Ollama estimates

P2: Guardrails (tools/executor.py)
  - Block dangerous commands (rm -rf, git push --force, drop database, etc.)
  - Protect sensitive files (.env, credentials.json, id_rsa)
  - Confine writes to project_root

P3: Execution observability (core/execution_trace.py)
  - Structured trace per task (steps, timing, tokens, success)
  - Human-readable summary() output

P4: Session continuity (memory/session_md.py)
  - Auto-save SESSION.md on exit (recent task summaries)
  - Auto-load on next startup into Gate memory_context
  - Based on Claude Code 4-Layer Memory + Augment "Session-End Spec Update"

Also fixed: apply_patch method accidentally dropped during executor.py rewrite.

311 tests passing.

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

2026-04-29 20:52:13 +08:00

..

__init__.py

Kaiwu v0.4: expert registry, flywheel, 3-layer memory, MCP router

2026-04-27 00:18:04 +08:00

expert_md.py

Kaiwu v0.4: expert registry, flywheel, 3-layer memory, MCP router

2026-04-27 00:18:04 +08:00

kaiwu_md.py

Kaiwu v0.4: expert registry, flywheel, 3-layer memory, MCP router

2026-04-27 00:18:04 +08:00

pattern_md.py

feat: DAG task compiler + prompt optimizer, remove Python expert system

2026-04-29 11:12:13 +08:00

project_md.py

v0.7.0: P1+P2+搜索重构+UI全面优化

2026-04-28 17:52:59 +08:00

session_md.py

feat: complete MoE framework — token budget, guardrails, observability, session continuity

2026-04-29 20:52:13 +08:00