[FEATURE]: Runtime model override for task tool subagents

[Quadina]

Feature hasn't been suggested before.

• I have verified this feature I'm about to request hasn't been suggested before.

Describe the enhancement you want to request

Problem: Subagents always run on the model configured at startup. There's no way for an orchestrating agent to switch models at runtime based on context.

Use cases:

1. Adaptive review loop — orchestrator runs code review on haiku. If the same errors repeat twice, it escalates to sonnet or opus for a more thorough review (fewer false positives, better understanding of context).
2. Variable-complexity reports — same report-generating subagent, but the orchestrator picks the model based on report difficulty. Simple report → cheap model. Complex/long report → stronger model. The agent definition stays the same.

Proposed approach: Add a model parameter to the task tool ("provider/model-id" format). Gate it with a new model_override permission (default: deny) so users control which models agents can switch to. Supports wildcards ("anthropic/*": "allow") and specific models.

Why permission-gated: Without it, a prompt injection could escalate to an expensive model, or an agent could pick models randomly. The permission system lets users whitelist exactly what's allowed.

Not a duplicate of #17570: That issue is about static config — users assign models to subagents upfront in config/UI. This is about runtime decisions — the orchestrating agent picks the model dynamically based on what's happening during execution (errors, complexity, retries). They're complementary features.

---

Note: PR #17577 with an implementation already exists — apologies for the reversed order. Opening this issue retroactively for proper tracking and design discussion.

[github-actions]

This issue might be a duplicate of existing issues. Please check:

• [FEATURE]: Dynamic model selection for subagents via Task tool #6651: Requests dynamic/runtime model selection for subagents via the Task tool — same core concept of an orchestrating agent picking the model per invocation based on task complexity
• [FEATURE]: @agent:provider/model syntax to override subagent model on the fly #11215: Requests per-invocation model override for subagents (@agent:provider/model syntax) — same goal of switching models at runtime without static config

If your request adds meaningfully different scope (e.g., the permission-gating mechanism or the specific runtime-escalation use cases), please clarify how it differs so maintainers can decide whether to merge or keep separate.