Evaluate: Cross-provider context serialisation for ADF multi-model routing

Parent Epic

#682 -- Evaluate Pi architectural patterns

Pattern

Pi's pi-ai layer supports cross-provider handoffs: switch models mid-session while serialising conversation context across different provider formats (Anthropic, OpenAI, Google, etc.). Context serialisation handles format differences transparently.

Current State

ADF (terraphim_orchestrator) routes different agents to different models via RoutingEngine:

• fastest -> Cerebras llama-3.3-70b (~300ms)
• think -> z.ai GLM-5 (reasoning)
• general -> z.ai GLM-4.7
• default -> Claude via claude -p

However, each agent runs in isolation. There is no mechanism to:

1. Hand off context from one model to another mid-task
2. Serialise a conversation from Claude format to OpenAI format for a second opinion
3. Use a cheaper model for initial analysis then escalate to a more capable model with the same context

Evaluation Questions

1. Is cross-provider handoff valuable for ADF? Current agents are independent. Would "start with Cerebras, escalate to Claude" improve cost/quality?
2. What does context serialisation look like in Rust? Pi does this in TypeScript. Rust implementation would need serde-based format converters for each provider's message schema.
3. Does this conflict with the Agent SDK direction? If we migrate ADF to Agent SDK (#682 context), we're locked to Claude. Cross-provider would only apply to non-SDK agents.
4. What's the minimal viable implementation? E.g., Anthropic <-> OpenAI message format converter as a standalone function.

Acceptance Criteria

• Identify 2-3 concrete ADF scenarios where cross-provider handoff would improve outcomes
• Prototype message format converter: Anthropic Messages API <-> OpenAI Chat Completions API
• Measure context loss (if any) during serialisation round-trip
• Decision: implement, defer, or reject with rationale

References

• Pi cross-provider handoffs: https://github.com/badlogic/pi-mono/tree/main/packages/ai (see "Cross-Provider Handoffs" section)
• ADF RoutingEngine: terraphim-ai/crates/terraphim_orchestrator/src/routing.rs
• terraphim_llm_proxy model routing: /etc/terraphim-llm-proxy/config.toml

Start by reading terraphim-ai/crates/terraphim_orchestrator/src/routing.rs and the referenced Pi cross-provider handoff implementation. Review the listed ADF routing scenarios and provider formats, then prototype the Anthropic Messages API ↔ OpenAI Chat Completions API conversion and measure round-trip context loss. Done means documenting the scenarios and a rationale to implement, defer, or reject the approach.