Experimental compaction improvements (prefix preservation + prompt customization)

Problem

When sessions are compacted, the system currently switches to a generic "compaction" agent, losing:

Original agent's tool definitions and system prompts
Specialized instructions or model-specific optimizations
→ 3. Prefix cache benefits for providers that implement caching (Claude, GPT-4, etc.)

Add experimental feature flags for:

OPENCODE_EXPERIMENTAL_COMPACTION_PRESERVE_PREFIX - Preserve original agent's prefix cache during compaction
additionally OPENCODE_EXPERIMENTAL_COMPACTION_PROMPT - Allow customizable compaction prompts

Performance: Cache hits for providers with prefix caching reduce token usage costs and latency up to 90%
Flexibility: Users can customize compaction prompts for their workflow
Gradual rollout: Experimental flags allow testing before stabilization

export OPENCODE_EXPERIMENTAL_COMPACTION_PRESERVE_PREFIX=true
export OPENCODE_EXPERIMENTAL_COMPACTION_PROMPT="Custom prompt if needed"

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

Auto-compaction causes the subagent to lose its original context, possibly the system prompt as well #6535: Subagent loses original context and system prompt during compaction
Soft compaction / AI global workspace metabolism #3032: Soft compaction / AI global workspace metabolism - proposes alternative compaction strategy to preserve context
[FEATURE] Sliding window context management for long-running sessions #4659: Sliding window context management for long-running sessions - addresses context preservation across compactions
[FEATURE]: Add systemPrompt option to SDK like Claude Agent SDK #7351: Add systemPrompt option to SDK - relates to the customizable compaction prompt aspect

Feel free to ignore if none of these address your specific case.

To stay organized issues are automatically closed after 90 days of no activity. If the issue is still relevant please open a new one.