fix(compaction): configurable summarizer tool_choice; wider overflow detection

Port of upstream grok-build 0.2.105 + 0.2.118.

- CompactionToolChoice (auto default | none), resolved env
  KIGI_COMPACTION_TOOL_CHOICE > [features].compaction_tool_choice >
  remote settings. Some OpenAI-compatible servers reject
  tool_choice:"none" with tools attached, failing every long-session
  compaction; auto keeps them working (the summarization prompt already
  forbids tool use). Threaded from agent + subagent spawn through
  CompactionConfig into generate_session_compact; the Responses gate
  counts hosted tools too, so a hosted-only request still carries the
  configured choice.
- is_context_length_error recognizes the "current message ... exceeds
  budget" phrasing, so that overflow is Fatal instead of burning the
  retry budget on a deterministic failure.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01KSy9S31pZNWXtRZNVJ1sDf

crates/codegen/kigi-shell/src/agent/mvp_agent/agent_ops.rs

@@ -2183,6 +2183,7 @@ impl MvpAgent {
             .cfg
             .borrow()
             .resolve_compaction_verbatim_input();
+        let compaction_tool_choice = self.cfg.borrow().resolve_compaction_tool_choice();
         let two_pass_enabled = self.cfg.borrow().is_two_pass_compaction_enabled();
         let auto_update = self.cfg.borrow().cli.auto_update;
         let client_type = *self.client_type.borrow();
@@ -2568,6 +2569,7 @@ impl MvpAgent {
                     system_prompt_label,
                     compaction_mode,
                     compaction_verbatim_input,
+                    compaction_tool_choice,
                     two_pass_enabled,
                     buffering_settings,
                     origin_client.clone(),