diff --git a/packages/coding-agent/CHANGELOG.md b/packages/coding-agent/CHANGELOG.md
index 54e221a4d..bf24d88c4 100644
--- a/packages/coding-agent/CHANGELOG.md
+++ b/packages/coding-agent/CHANGELOG.md
@@ -26,7 +26,7 @@
 
 ### Fixed
 
-- Stopped Mnemopi retention from overflowing the embedding model's context window: `embed()` now caps each input at `MNEMOPI_EMBEDDING_MAX_INPUT_CHARS` (default 8192 chars) so a long multi-turn `MnemopiSessionState.retainMessages` transcript can't make llama.cpp's `/embeddings` server reject the request with `request (N tokens) exceeds the available context size` and silently drop vector recall for that memory ([#3126](https://github.com/can1357/oh-my-pi/issues/3126)).
+- Stopped Mnemopi retention from overflowing the embedding model's context window: `embed()` now caps each input at `MNEMOPI_EMBEDDING_MAX_INPUT_CHARS` (default 8192 chars) and clips with a head/tail split so a long multi-turn `MnemopiSessionState.retainMessages` transcript can't make llama.cpp's `/embeddings` server reject the request with `request (N tokens) exceeds the available context size` and silently drop vector recall for that memory. The head/tail clip keeps both the opening setup and the most recent turns so later episodes don't collapse onto the same prefix vector ([#3126](https://github.com/can1357/oh-my-pi/issues/3126)).
 
 ## [16.1.7] - 2026-06-20
 
diff --git a/packages/mnemopi/CHANGELOG.md b/packages/mnemopi/CHANGELOG.md
index ba3a5658c..10bf70ac9 100644
--- a/packages/mnemopi/CHANGELOG.md
+++ b/packages/mnemopi/CHANGELOG.md
@@ -4,7 +4,7 @@
 
 ### Fixed
 
-- Capped per-input length in `embed()` at `MNEMOPI_EMBEDDING_MAX_INPUT_CHARS` (default 8192 chars, override via the env var or `embeddings.maxInputChars` runtime option; `0` disables) so a long retention transcript can no longer overflow the embedding model's context window. llama.cpp's `/embeddings` server used to reject the request with `request (N tokens) exceeds the available context size`, silently dropping vector recall for that memory ([#3126](https://github.com/can1357/oh-my-pi/issues/3126)).
+- Capped per-input length in `embed()` at `MNEMOPI_EMBEDDING_MAX_INPUT_CHARS` (default 8192 chars, override via the env var or `embeddings.maxInputChars` runtime option; `0` disables) so a long retention transcript can no longer overflow the embedding model's context window. Oversized inputs are clipped with a head/tail split so chronological transcripts keep both the opening setup and the most recent turns instead of losing the latest content under a naive prefix slice. llama.cpp's `/embeddings` server used to reject the request with `request (N tokens) exceeds the available context size`, silently dropping vector recall for that memory ([#3126](https://github.com/can1357/oh-my-pi/issues/3126)).
 
 ## [16.1.3] - 2026-06-19
 
diff --git a/packages/mnemopi/src/core/embeddings.ts b/packages/mnemopi/src/core/embeddings.ts
index 2d84ca7a1..d77448297 100644
--- a/packages/mnemopi/src/core/embeddings.ts
+++ b/packages/mnemopi/src/core/embeddings.ts
@@ -135,14 +135,39 @@ function effectiveMaxInputChars(): number {
 	return 8192;
 }
 
+/** Elision marker injected between the retained head and tail of an oversized input. */
+const EMBEDDING_ELISION_MARKER = "\n\n[...]\n\n";
+
 /**
- * Right-truncate every input to {@link effectiveMaxInputChars} so a runaway
- * retention transcript can't blow past the embedding model's context window.
- * Returns the original array when no input needs trimming (the common case);
- * the new array is allocated only when at least one input is oversized so
- * we don't churn arrays for the typical short-query path through `embedQuery`.
- * Emits one debug-or-warn log per call summarizing how many inputs were
- * trimmed and by how much — silent truncation was the original bug (#3126).
+ * Right-clip a single oversized input to {@link max} chars while preserving
+ * both ends. Retention transcripts are chronological (oldest → newest), so a
+ * naive `slice(0, max)` would drop the most recent — and most semantically
+ * loaded — turns once a session passed the cap, leaving every later retained
+ * episode with essentially the same prefix vector. Keeping a head/tail split
+ * lets the embedding capture the topic setup at the start AND the latest
+ * exchanges at the end. Falls back to a tail-only clip when `max` is too
+ * small to fit the elision marker plus a useful slice on either side.
+ */
+function clipToWindow(text: string, max: number): string {
+	if (text.length <= max) return text;
+	if (max <= EMBEDDING_ELISION_MARKER.length + 16) return text.slice(text.length - max);
+	const budget = max - EMBEDDING_ELISION_MARKER.length;
+	const headLen = budget >>> 1;
+	const tailLen = budget - headLen;
+	return text.slice(0, headLen) + EMBEDDING_ELISION_MARKER + text.slice(text.length - tailLen);
+}
+
+/**
+ * Clip every input to {@link effectiveMaxInputChars} so a runaway retention
+ * transcript can't blow past the embedding model's context window. Uses a
+ * head/tail split via {@link clipToWindow} so the embedding still sees the
+ * tail of the conversation (where the latest topic shifts live) and not just
+ * the stale prefix. Returns the original array when no input needs trimming
+ * (the common case); the new array is allocated only when at least one input
+ * is oversized so we don't churn arrays for the typical short-query path
+ * through `embedQuery`. Emits one debug-or-warn log per call summarizing how
+ * many inputs were trimmed and by how much — silent truncation was the
+ * original bug (#3126).
  */
 function capInputs(texts: readonly string[]): readonly string[] {
 	const max = effectiveMaxInputChars();
@@ -154,7 +179,7 @@ function capInputs(texts: readonly string[]): readonly string[] {
 		const text = texts[i] ?? "";
 		if (text.length <= max) continue;
 		if (trimmed === null) trimmed = texts.slice() as string[];
-		trimmed[i] = text.slice(0, max);
+		trimmed[i] = clipToWindow(text, max);
 		trimmedCount++;
 		if (text.length > maxOriginalLen) maxOriginalLen = text.length;
 	}
diff --git a/packages/mnemopi/test/embedding-input-cap.test.ts b/packages/mnemopi/test/embedding-input-cap.test.ts
index 46217ac3c..3cbe7275e 100644
--- a/packages/mnemopi/test/embedding-input-cap.test.ts
+++ b/packages/mnemopi/test/embedding-input-cap.test.ts
@@ -90,6 +90,27 @@ describe("embed() input cap (#3126)", () => {
 		expect(provider.calls[0]?.[0]?.length).toBe(256);
 	});
 
+	it("preserves both ends of a chronological transcript via the head/tail clip", async () => {
+		const provider = captureProvider();
+		setEmbeddingProviderForTests(provider);
+
+		// `MnemopiSessionState.retainMessages` hands `embed()` the full
+		// chronological transcript. Before the head/tail clip, a `slice(0, max)`
+		// would land on the oldest turns and drop the most recent (and most
+		// semantically loaded) content. Verify both ends survive.
+		const earliest = "OPENING_TURN_MARKER";
+		const latest = "FINAL_TURN_MARKER";
+		const transcript = `${earliest}${"x".repeat(50_000)}${latest}`;
+
+		await withEnvValue(undefined, () => embed([transcript]));
+
+		const seen = provider.calls[0]?.[0] ?? "";
+		expect(seen.length).toBe(8192);
+		expect(seen.startsWith(earliest)).toBe(true);
+		expect(seen.endsWith(latest)).toBe(true);
+		expect(seen).toContain("[...]");
+	});
+
 	it("returns the original array reference when no input needs trimming", async () => {
 		const provider = captureProvider();
 		setEmbeddingProviderForTests(provider);