Adapt corrections through PromptKit

docs/internal/llm.md

@@ -42,6 +42,14 @@ observability. The adapter returns PromptKit’s validated raw bytes rather than
 re-encoding the decoded target. An empty optional material is represented as
 one space so its named input is retained by PromptKit.
 
+When a request includes semantic correction material, the adapter validates and
+defensively copies it before preparation, then appends exactly two messages
+after the ordinarily rendered prompt: the prior response as an assistant
+message and the correction guidance as a user message. Requests without a
+correction do not add messages or introduce caller roles. Ordinary request
+summaries record correction byte counts and digests only; complete messages are
+available solely in an explicitly requested debug trace.
+
 Client construction may also receive a run-wide reasoning-effort override from
 the CLI factory boundary. The adapter copies the caller-owned pointer and
 creates a fresh PromptKit execution override for each request: a nil pointer

docs/roadmap/implementation.md

@@ -269,7 +269,7 @@ Capability is explicit, fingerprinted, and testable, while existing production
 pipelines remain executable pending their migrations. No dormant feature gate
 or unused preparation check is introduced. This stage is one Terra prompt.
 
-## Stage 5 — Adapt Corrections Through PromptKit
+## Stage 5 — Adapt Corrections Through PromptKit ✅
 
 ### Goal