chore(version): 1.5.7

Follow-on to the session-stability fix. "Per source" already made the
prefix cache hit, but it puts every conversation into one upstream session.

Using the client's own session id is not possible: capturing real agent
traffic (tcpdump on 127.0.0.1:8081) shows generic OpenAI clients send NO
session identifier at all — no user / session_id / conversation_id /
metadata in the body, and no session header (only X-Stainless-* plus
User-Agent: pi). The x-opencode-session the Go endpoint asks for is an
OpenCode native-client concept that a generic client cannot forward.

Since history is replayed every turn, the FIRST user message is invariant
for the life of a conversation, so it is used as the conversation
fingerprint. The session becomes stable within a conversation and distinct
across conversations; requests with no user message fall back to per-source
stability.

Measured through the gateway (same 5.7k-token prompt): 2nd call
cached_tokens=5504, and an unrelated conversation gets its own session.

Test: TestOpenCodeSessionIsStableForCache covers same-conversation
stability, cross-conversation separation, per-request request ids and the
sessionless fallback.

cmd/gui/package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "modelrouter-gui",
-  "version": "1.5.6",
+  "version": "1.5.7",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "modelrouter-gui",
-      "version": "1.5.6",
+      "version": "1.5.7",
       "license": "Proprietary",
       "devDependencies": {
         "electron": "^33.0.0",

cmd/gui/package.json

@@ -1,6 +1,6 @@
 {
   "name": "modelrouter-gui",
-  "version": "1.5.6",
+  "version": "1.5.7",
   "description": "ModelRouter Desktop — embedded ModelRouter core with tray",
   "author": "ModelRouter",
   "main": "main.js",

internal/lua/adapters/opencodego.lua

@@ -29,6 +29,39 @@ local function rand_id(prefix, seed)
     return prefix .. string.sub(sha256_hex(seed), 1, 24)
 end
 
+-- 会话指纹：取历史里**第一条 user 消息**。
+--
+-- 为什么不直接用客户端的会话 id：实测抓包（tcpdump 抓 127.0.0.1:8081 的真实
+-- agent 请求）确认通用 OpenAI 客户端**根本不发**任何会话标识 —— body 里没有
+-- user / session_id / conversation_id / metadata，请求头也只有 X-Stainless-*
+-- （OpenAI JS SDK）与 User-Agent。opencode 原生客户端那套 x-opencode-session
+-- 是它自己的概念，通用客户端无从转发。
+--
+-- 退而求其次但要够用：历史被逐轮重放，**第一条 user 消息在整个会话里恒定**，
+-- 用它做指纹即可得到"每会话一个 session"，而不是"每源一个 session"。
+-- 拿不到时（无 user 消息）返回空串，调用方回退到按源稳定。
+local function conversation_fingerprint(body)
+    if type(body) ~= "string" or body == "" then return "" end
+    local ok, req = pcall(json.decode, body)
+    if not ok or type(req) ~= "table" then return "" end
+    for _, m in ipairs(req.messages or {}) do
+        if type(m) == "table" and m.role == "user" then
+            local c = m.content
+            if type(c) == "string" then
+                if c ~= "" then return c end
+            elseif type(c) == "table" then
+                for _, part in ipairs(c) do
+                    if type(part) == "table" and part.type == "text" and part.text then
+                        return part.text
+                    end
+                end
+            end
+            return ""
+        end
+    end
+    return ""
+end
+
 function adapter.build_headers(meta)
     local ts = tostring(meta.timestamp or "")
     local src = (meta.source and meta.source.name) or ""
@@ -43,7 +76,7 @@ function adapter.build_headers(meta)
         --   每请求换 session -> 永远 0 命中
         -- 原先用 meta.timestamp 派生，等于每请求都是新会话，缓存永远无效，
         -- 上游也无法做会话亲和路由。
-        ["x-opencode-session"] = rand_id("ses_", "session|llmsproxy|" .. src),
+        ["x-opencode-session"] = rand_id("ses_", "session|llmsproxy|" .. src .. "|" .. conversation_fingerprint(meta.body)),
         -- request id 仍每请求唯一（它只是请求标识，不参与缓存键）
         ["x-opencode-request"] = rand_id("msg_", "request|" .. ts .. "|" .. tostring(meta.body or "")),
     }

internal/lua/adapters/opencodezen.lua

@@ -30,6 +30,39 @@ local function rand_id(prefix, seed)
     return prefix .. string.sub(sha256_hex(seed), 1, 24)
 end
 
+-- 会话指纹：取历史里**第一条 user 消息**。
+--
+-- 为什么不直接用客户端的会话 id：实测抓包（tcpdump 抓 127.0.0.1:8081 的真实
+-- agent 请求）确认通用 OpenAI 客户端**根本不发**任何会话标识 —— body 里没有
+-- user / session_id / conversation_id / metadata，请求头也只有 X-Stainless-*
+-- （OpenAI JS SDK）与 User-Agent。opencode 原生客户端那套 x-opencode-session
+-- 是它自己的概念，通用客户端无从转发。
+--
+-- 退而求其次但要够用：历史被逐轮重放，**第一条 user 消息在整个会话里恒定**，
+-- 用它做指纹即可得到"每会话一个 session"，而不是"每源一个 session"。
+-- 拿不到时（无 user 消息）返回空串，调用方回退到按源稳定。
+local function conversation_fingerprint(body)
+    if type(body) ~= "string" or body == "" then return "" end
+    local ok, req = pcall(json.decode, body)
+    if not ok or type(req) ~= "table" then return "" end
+    for _, m in ipairs(req.messages or {}) do
+        if type(m) == "table" and m.role == "user" then
+            local c = m.content
+            if type(c) == "string" then
+                if c ~= "" then return c end
+            elseif type(c) == "table" then
+                for _, part in ipairs(c) do
+                    if type(part) == "table" and part.type == "text" and part.text then
+                        return part.text
+                    end
+                end
+            end
+            return ""
+        end
+    end
+    return ""
+end
+
 function adapter.build_headers(meta)
     local ts = tostring(meta.timestamp or "")
     local src = (meta.source and meta.source.name) or ""
@@ -44,7 +77,7 @@ function adapter.build_headers(meta)
         --   每请求换 session -> 永远 0 命中
         -- 原先用 meta.timestamp 派生，等于每请求都是新会话，缓存永远无效，
         -- 上游也无法做会话亲和路由。
-        ["x-opencode-session"] = rand_id("ses_", "session|llmsproxy|" .. src),
+        ["x-opencode-session"] = rand_id("ses_", "session|llmsproxy|" .. src .. "|" .. conversation_fingerprint(meta.body)),
         -- request id 仍每请求唯一（它只是请求标识，不参与缓存键）
         ["x-opencode-request"] = rand_id("msg_", "request|" .. ts .. "|" .. tostring(meta.body or "")),
     }

internal/lua/toolcall_preservation_test.go

@@ -232,52 +232,72 @@ func TestOpenCodeGoVsZenReasoning(t *testing.T) {
 	}
 }
 
-// TestOpenCodeSessionIsStableForCache pins that the opencode client header set
+// TestOpenCodeSessionIsStableForCache pins the session-derivation contract that
-// keeps x-opencode-session STABLE per source while x-opencode-request stays
+// makes the upstream prefix cache usable.
-// unique per call.
 //
-// Measured against the live OpenCode Go endpoint: the upstream prefix cache is
+// Measured against the live OpenCode Go endpoint: the prefix cache is
-// session-scoped. Replaying the same 6032-token prompt hits 5888 cached tokens
+// SESSION-scoped. Replaying the same 6032-token prompt hits 5888 cached tokens
 // when the session id is fixed, and 0 when it changes per request. Deriving the
-// session from meta.timestamp (the previous behaviour) made every request a new
+// session from meta.timestamp (the previous behaviour) meant every request was a
-// session, so the cache could never hit.
+// new session, so the cache could never hit.
+//
+// The session must be stable WITHIN one conversation and differ BETWEEN
+// conversations. Since generic OpenAI clients send no session id at all
+// (verified by capturing real agent traffic: no user / session_id /
+// conversation_id / metadata in the body, no session header), the conversation
+// is fingerprinted by its FIRST user message — history is replayed every turn,
+// so that message is invariant for the life of the conversation.
 func TestOpenCodeSessionIsStableForCache(t *testing.T) {
 	for _, name := range []string{"opencodego", "opencodezen"} {
 		vm := NewVM(freshAdapterDir(t))
 		if err := vm.Start(); err != nil {
 			t.Fatal(err)
 		}
+		meta := func(ts int, body string) map[string]interface{} {
+			return map[string]interface{}{
+				"timestamp": ts,
+				"body":      body,
+				"source":    map[string]interface{}{"name": "somesource", "meta": nil},
+			}
+		}
 
-		metaA := map[string]interface{}{
+		// Same conversation, later turn: history grew, first user msg unchanged.
-			"timestamp": 1000,
+		h1, err := vm.BuildHeaders(name, meta(1000,
-			"body":      `{"messages":[{"role":"user","content":"one"}]}`,
+			`{"messages":[{"role":"user","content":"fix the bug"},{"role":"assistant","content":"looking"}]}`))
-			"source":    map[string]interface{}{"name": "somesource", "meta": nil},
-		}
-		metaB := map[string]interface{}{
-			"timestamp": 2000, // different second, different body
-			"body":      `{"messages":[{"role":"user","content":"two"}]}`,
-			"source":    map[string]interface{}{"name": "somesource", "meta": nil},
-		}
-		h1, err := vm.BuildHeaders(name, metaA)
 		if err != nil {
-			t.Fatalf("%s headers A: %v", name, err)
+			t.Fatalf("%s: %v", name, err)
 		}
-		h2, err := vm.BuildHeaders(name, metaB)
+		h2, err := vm.BuildHeaders(name, meta(2000,
+			`{"messages":[{"role":"user","content":"fix the bug"},{"role":"assistant","content":"looking"},{"role":"user","content":"and tests"}]}`))
 		if err != nil {
-			t.Fatalf("%s headers B: %v", name, err)
+			t.Fatalf("%s: %v", name, err)
+		}
+		// Different conversation.
+		h3, err := vm.BuildHeaders(name, meta(3000,
+			`{"messages":[{"role":"user","content":"an unrelated task"}]}`))
+		if err != nil {
+			t.Fatalf("%s: %v", name, err)
 		}
 
 		if h1["x-opencode-session"] == "" {
 			t.Fatalf("%s: session header must be set", name)
 		}
 		if h1["x-opencode-session"] != h2["x-opencode-session"] {
-			t.Errorf("%s: x-opencode-session must be stable across requests (%q vs %q) — "+
+			t.Errorf("%s: x-opencode-session must be STABLE across turns of one conversation "+
-				"the upstream prefix cache is session-scoped, a rotating session kills every cache hit",
+				"(%q vs %q) — the prefix cache is session-scoped", name, h1["x-opencode-session"], h2["x-opencode-session"])
-				name, h1["x-opencode-session"], h2["x-opencode-session"])
+		}
+		if h1["x-opencode-session"] == h3["x-opencode-session"] {
+			t.Errorf("%s: a different conversation must get a different session", name)
 		}
 		if h1["x-opencode-request"] == h2["x-opencode-request"] {
 			t.Errorf("%s: x-opencode-request must differ per request", name)
 		}
+		// No user message at all falls back to per-source stability.
+		h4, _ := vm.BuildHeaders(name, meta(4000, `{"messages":[{"role":"system","content":"s"}]}`))
+		h5, _ := vm.BuildHeaders(name, meta(5000, `{"messages":[{"role":"system","content":"s"}]}`))
+		if h4["x-opencode-session"] != h5["x-opencode-session"] {
+			t.Errorf("%s: sessionless requests must still be stable per source", name)
+		}
 		vm.Stop()
 	}
 }