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.

cli/src/agent.yaml

@@ -4,32 +4,37 @@ api: openai-responses
 # OpenAI base URLs include /v1. Do not include /responses or /chat/completions.
 base_url: https://api.openai.com/v1
 # model is the provider's model identifier.
-model: gpt-4.1
+model: gpt-6.1-sol
 # token is the API key. Replace CHANGE_ME with your key.
 # An empty token requires allow_no_token: true. Then no authentication header is sent.
 token: CHANGE_ME
 allow_no_token: false
+# thinking is how much the model thinks before it answers:
+# off, low, medium, high, xhigh, or max. Remove the line to use the model's default,
+# for example for a model without thinking.
+# If the model rejects a level, the agent uses the nearest level that the model accepts.
+# If the model cannot switch thinking off, off becomes low.
+# A caller can set another level for one turn: agent.chat {"text": "...", "thinking": "high"}.
+# The agent reads this file at the start of each turn, so a change applies to the next turn.
+thinking: medium
 # Optional output token cap. Anthropic defaults to 32000 if omitted.
 # max_tokens: 32000
-# Optional thinking effort: off, low, medium, high, xhigh, or max.
-# The agent retries a rejected effort with the nearest accepted level.
-# thinking: high
-# Optional OpenAI override for thinking effort.
-# reasoning_effort: high
 
 # OpenAI Responses example (base_url includes the version):
 # api: openai-responses
 # base_url: https://api.openai.com/v1
-# model: gpt-4.1
+# model: gpt-6.1-sol
 # token: YOUR_OPENAI_KEY
 # allow_no_token: false
+# thinking: medium
 
 # OpenRouter example (OpenAI Chat Completions, the format of most providers):
 # api: openai-chat-completions
 # base_url: https://openrouter.ai/api/v1
-# model: anthropic/claude-sonnet-4.5
+# model: anthropic/claude-sonnet-5.5
 # token: YOUR_OPENROUTER_KEY
 # allow_no_token: false
+# thinking: medium
 
 # Local Ollama example (OpenAI Chat Completions, no key):
 # api: openai-chat-completions
@@ -41,6 +46,7 @@ allow_no_token: false
 # Anthropic Messages example (base_url excludes the version):
 # api: anthropic-messages
 # base_url: https://api.anthropic.com
-# model: claude-sonnet-4-5
+# model: claude-sonnet-5-5
 # token: YOUR_ANTHROPIC_KEY
 # allow_no_token: false
+# thinking: medium