diff --git a/group_vars/mac/main.yml b/group_vars/mac/main.yml index b9d53dd..d73253e 100644 --- a/group_vars/mac/main.yml +++ b/group_vars/mac/main.yml @@ -59,19 +59,25 @@ hermes_settings: # /model deepseek or /model haiku in Telegram; add --once for one reply. model_aliases.deepseek: {model: deepseek/deepseek-v4.1-flash, provider: openrouter} model_aliases.haiku: {model: anthropic/claude-haiku-5.5, provider: openrouter} - # Side tasks would otherwise run on the chat model ("auto"). GLM-5.3 Flash - # is the cheapest model with credible Hermes scores; its slow first token - # doesn't matter here. Vision, voice and /review stay on the chat model. + # Side tasks would otherwise run on the chat model ("auto"). Vision, voice + # and /review stay on the chat model. + # Short-answer tasks turn reasoning off and allow only a few tokens (the + # approval guardian: 16, titles: 64). GLM-5.3 Flash can't turn reasoning off + # (OpenRouter: reasoning mandatory), spends the budget thinking and returns + # nothing, so the guardian escalated every command to you. Haiku 5.5 has + # reasoning off by default. + auxiliary.approval.provider: openrouter + auxiliary.approval.model: anthropic/claude-haiku-5.5 + auxiliary.title_generation.provider: openrouter + auxiliary.title_generation.model: anthropic/claude-haiku-5.5 + auxiliary.memory_query_rewrite.provider: openrouter + auxiliary.memory_query_rewrite.model: anthropic/claude-haiku-5.5 + auxiliary.mcp.provider: openrouter + auxiliary.mcp.model: anthropic/claude-haiku-5.5 + # Longer tasks: GLM-5.3 Flash is the cheapest model with credible Hermes + # scores; its slow first token doesn't matter here. auxiliary.compression.provider: openrouter auxiliary.compression.model: z-ai/glm-5.3-flash - auxiliary.approval.provider: openrouter - auxiliary.approval.model: z-ai/glm-5.3-flash - auxiliary.title_generation.provider: openrouter - auxiliary.title_generation.model: z-ai/glm-5.3-flash - auxiliary.mcp.provider: openrouter - auxiliary.mcp.model: z-ai/glm-5.3-flash - auxiliary.memory_query_rewrite.provider: openrouter - auxiliary.memory_query_rewrite.model: z-ai/glm-5.3-flash auxiliary.curator.provider: openrouter auxiliary.curator.model: z-ai/glm-5.3-flash auxiliary.monitor.provider: openrouter diff --git a/roles/mac/README.md b/roles/mac/README.md index 3126790..a6a7006 100644 --- a/roles/mac/README.md +++ b/roles/mac/README.md @@ -28,8 +28,8 @@ Manages cogitator-02, an Apple Silicon Mac on the tailnet (`mac.yml`, and the dashboard. Covers update backups, timezone, not borrowing Claude Code's login, sandbox memory, disabled toolsets, skill-write approval, deny rules, streaming, - voice-note transcription, and models: chat on GPT-6.1 Sol, side tasks and - cron on GLM-5.3 Flash, subagents on DeepSeek V4.1 Flash, `/model` aliases. + voice-note transcription, and models: chat on GPT-6.1 Sol, short side tasks + (approval, titles) on Claude Haiku 5.5, longer ones and cron on GLM-5.3 Flash, subagents on DeepSeek V4.1 Flash, `/model` aliases. Keys in `hermes_settings_force` are set with `--force` (Hermes reads `agent.reasoning_effort` but `config set` refuses it, hermes-agent #140221). - **MCP servers and secrets** (also tag `hermes-settings`): MCP servers are