docs(orchestration): never pick a worker model the user did not name (#19109)

The sonnet examples were added for a test cohort. Orchestration must not
choose a model on the user's behalf: pass --model only when the user named
one, otherwise inherit the configured agent default.

skill-guides/orchestration.md

@@ -104,7 +104,7 @@ waiting. `worker-start --spec` creates the Task and its attempt in one call:
 ORCA status --json
 ORCA orchestration run-create --objective "<objective>" --json
 ORCA orchestration worker-start --spec "<worker A task>" --worktree current --agent codex --json
-ORCA orchestration worker-start --spec "<worker B task>" --worktree current --agent claude --model sonnet --json
+ORCA orchestration worker-start --spec "<worker B task>" --worktree current --agent claude --json
 ORCA orchestration check --wait --types "worker_done,escalation,question" --timeout-ms 900000 --json
 ```
 

skill-guides/orchestration/references/coordinator-loop.md

@@ -22,12 +22,11 @@ when an older CLI rejects the flag. A nested worker must respect
 ## Launch preferences
 
 For a fresh Claude, Codex, or Cursor terminal, `--model` accepts an opaque
-provider model ID. Pick the cheapest model that fits the Task (`sonnet` for
-routine work); an omitted model inherits the launcher's default, often the most
-expensive. Add `--effort` only when that model supports it:
+provider model ID. Pass it only when the user named a model; otherwise omit it
+so the worker inherits the user's configured agent default. Add `--effort` only
+when that model supports it:
 
 ```text
-ORCA orchestration worker-start --task <task_id> --worktree current --agent claude --model sonnet --json
 ORCA orchestration worker-start --task <task_id> --worktree current --agent claude --model opus --effort high --json
 ```