diff --git a/src/agents/pi-embedded-helpers/provider-error-patterns.test.ts b/src/agents/pi-embedded-helpers/provider-error-patterns.test.ts
index 86dc42759c5..0e7bfbed0e4 100644
--- a/src/agents/pi-embedded-helpers/provider-error-patterns.test.ts
+++ b/src/agents/pi-embedded-helpers/provider-error-patterns.test.ts
@@ -50,6 +50,11 @@ describe("matchesProviderContextOverflow", () => {
     // Cohere
     "total tokens exceeds the model's maximum limit of 4096",
 
+    // llama.cpp HTTP server (slot ctx-size overflow)
+    "400 request (66202 tokens) exceeds the available context size (65536 tokens), try increasing it",
+    "request (130000 tokens) exceeds available context size (131072 tokens)",
+    "prompt (8500 tokens) exceeds the available context size (8192 tokens), try increasing it",
+
     // Generic
     "input is too long for model gpt-5.4",
   ])("matches provider-specific overflow: %s", (msg) => {
@@ -113,6 +118,15 @@ describe("isContextOverflowError with provider patterns", () => {
     expect(isContextOverflowError("ollama error: context length exceeded")).toBe(true);
   });
 
+  it("detects llama.cpp slot ctx-size overflow", () => {
+    // Native llama.cpp HTTP server overflow surfaced through openai-completions providers.
+    expect(
+      isContextOverflowError(
+        "400 request (66202 tokens) exceeds the available context size (65536 tokens), try increasing it",
+      ),
+    ).toBe(true);
+  });
+
   it("still detects standard context overflow patterns", () => {
     expect(isContextOverflowError("context length exceeded")).toBe(true);
     expect(isContextOverflowError("prompt is too long: 150000 tokens > 128000 maximum")).toBe(true);
diff --git a/src/agents/pi-embedded-helpers/provider-error-patterns.ts b/src/agents/pi-embedded-helpers/provider-error-patterns.ts
index 63c464a0fa3..96e16d99bd5 100644
--- a/src/agents/pi-embedded-helpers/provider-error-patterns.ts
+++ b/src/agents/pi-embedded-helpers/provider-error-patterns.ts
@@ -35,6 +35,13 @@ export const PROVIDER_CONTEXT_OVERFLOW_PATTERNS: readonly RegExp[] = [
   // Cohere does not currently ship a bundled provider hook.
   /\btotal tokens?.*exceeds? (?:the )?(?:model(?:'s)? )?(?:max|maximum|limit)/i,
 
+  // llama.cpp HTTP server (often used directly or behind an OpenAI-compatible
+  // shim) returns "request (N tokens) exceeds the available context size
+  // (M tokens), try increasing it" when the prompt overshoots a slot's
+  // ctx-size. Wording is from the upstream slot manager and is stable.
+  // Example: "400 request (66202 tokens) exceeds the available context size (65536 tokens), try increasing it"
+  /\b(?:request|prompt) \(\d[\d,]*\s*tokens?\) exceeds (?:the )?available context size\b/i,
+
   // Generic "input too long" pattern that isn't covered by existing checks
   /\binput (?:is )?too long for (?:the )?model\b/i,
 ];