Djordje Lukic 36903dd4c6 Cycle model thinking level with shift+tab ...

Pressing Shift+Tab in the TUI now cycles the current model's
thinking-effort level through its provider-specific range (e.g.
off → minimal → low → medium → high → xhigh for OpenAI), wrapping
around. The selected level is applied as a runtime model override
for the active session.

The current level is shown inline in the sidebar's agent block as
`<provider>/<model> • <thinking>`. To avoid a tool-count flicker,
the change refreshes only agent/team info via a new lightweight
Runtime.EmitAgentInfo instead of re-running full startup info (which
re-discovers tools).

Models that don't support reasoning, and remote runtimes, are
no-ops with an informational message.

Signed-off-by: Djordje Lukic <djordje.lukic@docker.com>

2026-06-11 00:28:22 +02:00

..

printer_test.go

Special case for single item lists

2025-12-24 21:04:48 +01:00

printer.go

Hide agent name header when stdout is not a TTY

2026-03-20 18:52:42 +01:00

runner_test.go

Cycle model thinking level with shift+tab

2026-06-11 00:28:22 +02:00

runner.go

Rename OAuth elicitation meta keys from cagent/ to docker-agent/

2026-05-28 15:23:53 +02:00