feat(context): compression pipeline stage 1 — level policy + deterministic stages

Additive CompressionPolicy (levels 1-9), ProtectedSpanTagger (regex load-bearing spans), FormatCompressor (json→dotted lines), ContextClassifier (static/structured/freeform). Stage 1 (FORMAT_COMPRESS) wired into DefaultContextPackBuilder behind the policy; structured entries only, lossless. PromptRenderer repetition-anchoring of steering directives.
2026-07-01 13:53:19 +04:00
parent 4be8f292ae
commit 61be90070f
8 changed files with 302 additions and 2 deletions
@@ -0,0 +1,78 @@
+import com.correx.core.context.compression.CompressionPolicy
+import com.correx.core.context.compression.CompressionStage
+import com.correx.core.context.compression.ContextClass
+import com.correx.core.context.compression.ContextClassifier
+import com.correx.core.context.compression.FormatCompressor
+import com.correx.core.context.compression.ProtectedSpanTagger
+import com.correx.core.context.model.ContextEntry
+import com.correx.core.context.model.ContextLayer
+import com.correx.core.context.model.EntryRole
+import com.correx.core.events.types.ContextEntryId
+import org.junit.jupiter.api.Assertions.assertEquals
+import org.junit.jupiter.api.Assertions.assertFalse
+import org.junit.jupiter.api.Assertions.assertTrue
+import org.junit.jupiter.api.Test
+
+class CompressionPipelineStagesTest {
+
+    private fun entry(sourceType: String, layer: ContextLayer, role: EntryRole, content: String = "x") =
+        ContextEntry(
+            id = ContextEntryId("e"),
+            layer = layer,
+            content = content,
+            sourceType = sourceType,
+            sourceId = "s",
+            tokenEstimate = 1,
+            role = role,
+        )
+
+    @Test
+    fun `levels are additive`() {
+        val l1 = CompressionPolicy(1)
+        assertTrue(l1.enabled(CompressionStage.FORMAT_COMPRESS))
+        assertFalse(l1.enabled(CompressionStage.CACHE_STATIC))
+
+        val l7 = CompressionPolicy(7)
+        // includes everything from 1..7
+        assertTrue(l7.enabled(CompressionStage.FORMAT_COMPRESS))
+        assertTrue(l7.enabled(CompressionStage.FACT_SHEET))
+        assertTrue(l7.enabled(CompressionStage.PROTECTED_SPAN_TAG))
+        assertFalse(l7.enabled(CompressionStage.TOME_MERGE)) // level 8
+    }
+
+    @Test
+    fun `protected spans capture ids numbers paths and code`() {
+        val tagger = ProtectedSpanTagger(extraEntities = listOf("GatedDeltaNet"))
+        val spans = tagger.protectedSpans(
+            "connect to 10.0.0.1 at path /etc/nginx.conf value 0xFF port = 8080 " +
+                "`inline` on GatedDeltaNet"
+        )
+        assertTrue(spans.any { it == "10.0.0.1" }, spans.toString())
+        assertTrue(spans.any { it.contains("/etc/nginx.conf") }, spans.toString())
+        assertTrue(spans.any { it == "0xFF" }, spans.toString())
+        assertTrue(spans.any { it == "`inline`" }, spans.toString())
+        assertTrue(spans.contains("GatedDeltaNet"), spans.toString())
+        assertTrue(spans.any { it == "8080" }, spans.toString())
+    }
+
+    @Test
+    fun `format compressor flattens json and preserves exact values`() {
+        val out = FormatCompressor().compress("""{"a":{"b":1},"c":"10.0.0.1"}""")
+        assertEquals("a.b = 1\nc = 10.0.0.1", out)
+    }
+
+    @Test
+    fun `format compressor leaves non-json content untouched`() {
+        val out = FormatCompressor().compress("log line\nlog line\nother")
+        assertEquals("log line\nlog line\nother", out)
+    }
+
+    @Test
+    fun `classifier separates static structured freeform`() {
+        val c = ContextClassifier()
+        assertEquals(ContextClass.STATIC, c.classify(entry("systemPrompt", ContextLayer.L0, EntryRole.SYSTEM)))
+        assertEquals(ContextClass.STRUCTURED, c.classify(entry("toolLog", ContextLayer.L2, EntryRole.TOOL)))
+        assertEquals(ContextClass.STRUCTURED, c.classify(entry("steeringNote", ContextLayer.L2, EntryRole.SYSTEM)))
+        assertEquals(ContextClass.FREEFORM, c.classify(entry("chat", ContextLayer.L1, EntryRole.USER)))
+    }
+}