agent: a thinking level in agent.yaml and per call

- thinking (off, low, medium, high, xhigh, max) is an enum: serde rejects
  unknown levels in the config, and the schema of agent.chat lists them.
  reasoning_effort, a second name for the same setting, is gone.
- agent.chat takes an optional thinking level for one turn.
- off really switches thinking off: OpenAI gets the effort none, and
  Anthropic gets disabled thinking (newer Claude models think by
  default). A model that cannot switch thinking off gets low.
- Unset means the model's default. Anthropic thinking blocks now return
  unless thinking is off, because newer models think by default.
- The template sets thinking: medium and shows it in each example, with
  current model names.
- Checked against the proxy with gpt-6-luna, glm-5.3-flash, and
  claude-haiku-5-5.

README.md

@@ -30,7 +30,7 @@ nix run git+https://gitea.surma.technology/surma/sausage -- run    # starts the
 
 `init` asks nothing. It writes `world/config/agent.yaml`, with a comment for
 each field and an example for each API. Edit it before the first chat: choose
-the API, the base URL, the model, and the key. Until then, a chat answers with
+the API, the base URL, the model, the key, and the thinking level. Until then, a chat answers with
 an error that names the missing field. Both commands take another folder as
 an argument, for example `... -- run my-world`.