# Changelog

## Score

- CAI 47 → 39 (-7.9)
- Rubric changed (rubric-2026.08.18 → rubric-2026.08.15) — scores are not directly comparable.

## Lenses

- Code Health 56 → 47 (-8.8)
- Architecture 96 → 97 (+0.2)
- Maturity 65 → 67 (+1.9)
- Readiness 47 → 22 (-24.9)
- Security 46 → 48 (+2.4)

## Resolved (629)

- (anonymous) (cognitive 17) (channel/web/static/js/console.js)
- (anonymous) (cognitive 21) (channel/web/static/js/console.js)
- (anonymous) (cognitive 24) (channel/web/static/js/console.js)
- (anonymous) (cognitive 39) (channel/web/static/js/console.js)
- Agent._estimate_message_tokens (cognitive 18) (agent/protocol/agent.py)
- Agent._get_model_context_window (cognitive 18) (agent/protocol/agent.py)
- Agent.compact_context (cognitive 20) (agent/protocol/agent.py)
- AgentBridge._migrate_config_to_env (cognitive 26) (bridge/agent_bridge.py)
- AgentBridge.agent_reply (cognitive 78) (bridge/agent_bridge.py)
- AgentBridge.agent_reply (cyclomatic 57) (bridge/agent_bridge.py)
- AgentInitializer._filter_text_only_messages (cognitive 16) (bridge/agent_initializer.py)
- AgentInitializer._flush_all_agents (cognitive 24) (bridge/agent_initializer.py)
- AgentInitializer._flush_all_agents (cyclomatic 16) (bridge/agent_initializer.py)
- AgentInitializer._initialize_scheduler (cognitive 36) (bridge/agent_initializer.py)
- AgentInitializer._load_tools (cognitive 48) (bridge/agent_initializer.py)
- AgentInitializer._load_tools (cyclomatic 22) (bridge/agent_initializer.py)
- AgentInitializer._migrate_config_to_env (cognitive 26) (bridge/agent_initializer.py)
- AgentLLMModel.call (cognitive 19) (bridge/agent_bridge.py)
- AgentLLMModel.call_stream (cognitive 21) (bridge/agent_bridge.py)
- AgentStreamExecutor._aggressive_trim_for_overflow (cognitive 60) (agent/protocol/agent_stream.py)
- …and 609 more

## New (108)

- (anonymous) (cognitive 16) (channel/web/static/js/console.js)
- (anonymous) (cognitive 16) (channel/web/static/js/workspace.js)
- (anonymous) (cognitive 19) (channel/web/static/js/console.js)
- (anonymous) (cognitive 22) (channel/web/static/js/console.js)
- (anonymous) (cognitive 44) (channel/web/static/js/console.js)
- Coverage not measured — test suite did not build
- Dimension evaluation failed
- Duplicated block (10 lines × 2) (channel/wechatmp/wechatmp_message.py)
- Duplicated block (10 lines × 2) (skills/image-generation/scripts/generate.py)
- Duplicated block (10 lines × 3) (plugins/tool/tool.py)
- Duplicated block (11 lines × 2) (tests/test_minimax_provider.py)
- Duplicated block (12 lines × 2) (channel/web/web_channel.py)
- Duplicated block (12 lines × 2) (plugins/cow_cli/cow_cli.py)
- Duplicated block (13 lines × 2) (agent/protocol/agent_stream.py)
- Duplicated block (15 lines × 2) (models/openai/openai_http_client.py)
- Duplicated block (16 lines × 2) (channel/wecom_bot/wecom_bot_channel.py)
- Duplicated block (16 lines × 2) (models/claudeapi/claude_api_bot.py)
- Duplicated block (16 lines × 3) (channel/web/web_channel.py)
- Duplicated block (17 lines × 2) (agent/tools/send/send.py)
- Duplicated block (18 lines × 2) (channel/feishu/feishu_channel.py)
- …and 88 more