Carry proposal exchanges into repair replay

docs/internal/llm-runtime.md

@@ -16,6 +16,8 @@ credential source names for artifact redaction without inspecting unrelated
 environment values. See the [integration contract](../integrations/openai-compatible-llm.md)
 for failure behavior and the [configuration reference](../config.md) for sources.
 
+Proposal calls can retain the original prompt, effective variables, prepared messages, and final response for section-local repair replay. The adapter renders the repair definition with the selected profile, appends branch history to the original prompt, and checks the prepared prefix before execution. The requested repair definition is retained in call attribution alongside the native base-prompt metadata.
+
 The observation collector tracks logical calls and execution events. Ordinary
 reports use compact safe outcomes; request and response evidence is optional
 debug material. The runner preserves ordered pipeline traversal and deterministic

docs/roadmap/implementation.md

@@ -93,6 +93,8 @@ validator responses remains [deferred](future.md#domain-aware-response-recovery)
 
 ## Stage 3 — Carry the original exchange through proposal generation and the adapter
 
+**Completed.**
+
 1. Use `internal/framework/structuredoutput` for internal conversation data
    shared by the role client and runner. Extend the existing structured request
    with optional repair replay data. Keep the repair definition as the