feat: per-agent LLM configuration (model and provider key)

Summary

Currently, model routing and LLM provider API keys are configured at the instance level and shared across all agents. There is no way to assign a specific model or provider key to an individual agent.

Problem

Model routing is global

The worker resolves its model without any agent context:

// src/agent/worker.rs
let model_name = routing.resolve(ProcessType::Worker, None).to_string();
//                                                          ^^^^ no agent context

All agents in the instance use the same model, determined solely by the global routing config.

Provider API keys are global

LLM provider keys are defined once under [llm.provider.*] and apply to every agent. There is no way to assign a per-agent billing key or use a different provider for a specific agent.

Expected Behavior

Agent configuration should support optional LLM overrides:

[agents.my-agent]
# override the global default model for this agent
model = "gpt-4o-mini"

# override the provider API key for this agent
llm_api_key = "secret:MY_AGENT_OPENAI_KEY"

When set, these values take precedence over the global routing and provider config for that agent only. Agents without overrides continue to use the global defaults.

Use Cases

• Different agents have different performance or cost requirements (lightweight tasks → small model, complex tasks → large model)
• Multiple users sharing one instance each want to use their own API key and preferred model
• Gradual model migration: test a new model on one agent before rolling it out globally

Related

• #354 — per-agent secret store isolation (separate but related multi-tenancy concern)

Start with src/agent/worker.rs, especially the routing call shown in the issue, then trace the existing agent configuration and global LLM provider settings. Done means agents can optionally select their own model and provider key while agents without overrides retain the global defaults.