From a39b3c4af49aec5c8ab34d8f2696d7c8bdbae076 Mon Sep 17 00:00:00 2001
From: mlsmaycon <mlsmaycon@gmail.com>
Date: Tue, 11 Aug 2026 13:04:41 +0000
Subject: [PATCH] [proxy] Anchor the Anthropic date strip to Claude ids

The release-date normalizer matched a bare "-YYYYMMDD" suffix on any id.
Pricing looks every model up through it regardless of surface, and an
operator can register a custom model under any id at all, so a custom
"internal-llm-20250101" would silently inherit the rate registered for
"internal-llm".

Anchor the pattern on "claude" so it still covers the vendor-prefixed
Bedrock forms while leaving every other vendor's id untouched.
---
 shared/llm/model.go      | 27 ++++++++++++++++-----------
 shared/llm/model_test.go | 28 ++++++++++++++++++----------
 2 files changed, 34 insertions(+), 21 deletions(-)

diff --git a/shared/llm/model.go b/shared/llm/model.go
index 95a6f694e..4fb631520 100644
--- a/shared/llm/model.go
+++ b/shared/llm/model.go
@@ -46,20 +46,25 @@ func NormalizeBedrockModel(modelID string) string {
 	return bedrockVersionSuffix.ReplaceAllString(m, "")
 }
 
-// anthropicDateSuffix matches the trailing "-YYYYMMDD" release-date suffix
-// Anthropic appends to a pinned model id. No other vendor in the catalog
-// ends an id in eight consecutive digits, so the pattern is safe to apply
-// before a lookup regardless of surface.
-var anthropicDateSuffix = regexp.MustCompile(`-\d{8}$`)
+// anthropicDatedModel matches a Claude model id carrying the trailing
+// "-YYYYMMDD" release-date suffix Anthropic appends to a pinned release,
+// capturing the id without it. The "claude" anchor is load-bearing: pricing
+// looks every model up through this helper regardless of surface, and an
+// operator may register a custom id with any shape at all, so an unanchored
+// "-\d{8}$" would let "internal-llm-20250101" silently inherit the rate
+// registered for "internal-llm". The anchor also covers the vendor-prefixed
+// forms ("anthropic.claude-...", "us.anthropic.claude-...").
+var anthropicDatedModel = regexp.MustCompile(`(?i)^(.*claude.*)-\d{8}$`)
 
 // NormalizeAnthropicModel strips the trailing release-date suffix from a
-// first-party Anthropic model id, e.g. "claude-sonnet-4-5-20250929" ->
-// "claude-sonnet-4-5", so a dated id a client pins matches the undated one
-// the operator registered. Callers try the verbatim id first and fall back
-// to this, so two dated releases of the same family stay distinct wherever
-// both are registered explicitly.
+// Claude model id, e.g. "claude-sonnet-4-5-20250929" -> "claude-sonnet-4-5",
+// so a dated id a client pins matches the undated one the operator
+// registered. Ids that are not Claude-family are returned untouched.
+// Callers try the verbatim id first and fall back to this, so two dated
+// releases of the same family stay distinct wherever both are registered
+// explicitly.
 func NormalizeAnthropicModel(modelID string) string {
-	return anthropicDateSuffix.ReplaceAllString(modelID, "")
+	return anthropicDatedModel.ReplaceAllString(modelID, "$1")
 }
 
 // NormalizeVertexModel strips the "@version" suffix from a Vertex AI model id
diff --git a/shared/llm/model_test.go b/shared/llm/model_test.go
index c1d5b63f6..5ce2ff497 100644
--- a/shared/llm/model_test.go
+++ b/shared/llm/model_test.go
@@ -37,16 +37,24 @@ func TestNormalizeVertexModel(t *testing.T) {
 
 func TestNormalizeAnthropicModel(t *testing.T) {
 	cases := map[string]string{
-		"claude-sonnet-4-5-20250929": "claude-sonnet-4-5",
-		"claude-3-5-haiku-20241022":  "claude-3-5-haiku",
-		"claude-sonnet-5":            "claude-sonnet-5",
-		"claude-opus-4-8":            "claude-opus-4-8",
-		// Other vendors' ids must survive untouched: none of them end in
-		// eight consecutive digits.
-		"gpt-4o":                     "gpt-4o",
-		"gpt-4o-2024-08-06":          "gpt-4o-2024-08-06",
-		"anthropic.claude-haiku-4-5": "anthropic.claude-haiku-4-5",
-		"":                           "",
+		"claude-sonnet-4-5-20250929":            "claude-sonnet-4-5",
+		"claude-3-5-haiku-20241022":             "claude-3-5-haiku",
+		"claude-sonnet-5":                       "claude-sonnet-5",
+		"claude-opus-4-8":                       "claude-opus-4-8",
+		"anthropic.claude-haiku-4-5":            "anthropic.claude-haiku-4-5",
+		"anthropic.claude-sonnet-4-5-20250929":  "anthropic.claude-sonnet-4-5",
+		"us.anthropic.claude-opus-4-8-20250101": "us.anthropic.claude-opus-4-8",
+		// Non-Claude ids must survive untouched even when they end in eight
+		// consecutive digits: an operator can register a custom model under
+		// any id, and pricing looks every one of them up through this helper.
+		"gpt-4o":                  "gpt-4o",
+		"gpt-4o-2024-08-06":       "gpt-4o-2024-08-06",
+		"gpt-4o-20240806":         "gpt-4o-20240806",
+		"internal-llm-20250101":   "internal-llm-20250101",
+		"deepseek-r1-20250120":    "deepseek-r1-20250120",
+		"Qwen/Qwen2.5-20250101":   "Qwen/Qwen2.5-20250101",
+		"gemini-2-5-pro-20250101": "gemini-2-5-pro-20250101",
+		"":                        "",
 	}
 	for in, want := range cases {
 		require.Equal(t, want, NormalizeAnthropicModel(in), "normalize %q", in)