feat(context): role means message type, layer means pinning (#312/#313)

The system block is now for content that does not change during a run.
Anything the run mutates renders as a user message — both because a
mutating system prefix defeats prompt caching and because models
under-weight system-folded content against the trailing user turn.

PromptRenderer: role alone decides the message type; the old
`layer == L0 ||` clause is gone. That clause was silently overriding
role on four packs (InferenceSummarizer, SemanticReviewerImpl,
CapabilityGapReflectorImpl, Talkie session-naming) which are L0+USER
prompts — they were rendering as a system-only request with no user
turn at all.

Re-roled SYSTEM -> USER, all mutable within a run:
  recoveryTicket, remainingDelta, groundingFeedback, rejectionFeedback
  (trailing slot), plus verifiedBaseline, promotedConcept, claimedTask,
  clarificationAnswer, locked steeringNote, factSheet (inline, still
  L0-pinned).
Left SYSTEM (immutable): systemPrompt, operatingGuidance,
schemaInstruction, projectProfile, operatorProfile, agentInstructions,
successfulPlanShape.

Trailing-slot scarcity guard: repairMandateSourceTypes joined ALL
matches, so a recovery stage on a retry with an unmet delta would stack
three competing mandates. Now a precedence list emits exactly one
(recoveryTicket > retryFeedback > groundingFeedback > rejectionFeedback)
with remainingDelta appended as the completion signal.

ContextClassifier keys STATIC on layer alone — L0 means pinned/never
pruned regardless of role, so the re-roled L0 entries don't fall through
to FREEFORM and get token-pruned.

Also fixes a stale ContextFeedbackTest assertion (expected a CAS hash
the producer deliberately stopped emitting) and a stale initialIntent
doc comment claiming L0/SYSTEM where the code says L1/USER.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

testing/kernel/src/test/kotlin/ContextFeedbackTest.kt

@@ -38,6 +38,7 @@ import com.correx.core.transitions.graph.TransitionEdge
 import com.correx.core.transitions.graph.WorkflowGraph
 import com.correx.testing.fixtures.EventFixtures.stored
 import org.junit.jupiter.api.Assertions.assertEquals
+import org.junit.jupiter.api.Assertions.assertFalse
 import org.junit.jupiter.api.Assertions.assertNull
 import org.junit.jupiter.api.Assertions.assertTrue
 import org.junit.jupiter.api.Test
@@ -95,10 +96,10 @@ class ContextFeedbackTest {
         val entry = buildRetryFeedbackEntry(events, StageId("impl"))!!
         assertTrue(entry.content.contains("## Retry repair state"), "content: ${entry.content}")
         assertTrue(entry.content.contains("gate 'execution'"), "content: ${entry.content}")
-        assertTrue(
-            entry.content.contains("frontend/src/hooks/queries.ts — CAS cafebabe"),
-            "content: ${entry.content}",
-        )
+        // Path only: the raw CAS hash is opaque noise the model can't act on and confuses it into
+        // reasoning about hashes — it patches by path via file_read/file_write.
+        assertTrue(entry.content.contains("- frontend/src/hooks/queries.ts"), "content: ${entry.content}")
+        assertFalse(entry.content.contains("cafebabe"), "content: ${entry.content}")
         assertTrue(entry.content.contains("do NOT re-read"), "content: ${entry.content}")
     }