chore(version): 1.5.6

The opencode adapters derived x-opencode-session from meta.timestamp, i.e. a
brand new session on every request. The upstream prefix cache is
session-scoped, so no request could ever hit it, and the cache fields the
endpoint does report (prompt_tokens_details.cached_tokens,
prompt_cache_hit_tokens/prompt_cache_miss_tokens) always came back 0/absent.

Measured against the live endpoint, same 6032-token prompt:

  fixed session id   -> 2nd call: hit 5888, miss 144
  rotating session id -> every call: hit 0, miss 6032

Fix: derive the session from the source name (stable), matching how
x-opencode-project is already derived. x-opencode-request stays unique per
request — it is only a request identifier, not part of the cache key.
Applied to both opencodego and opencodezen.

Through the gateway the same prompt now reports, on the 2nd call:
  details={'cached_tokens': 5888} hit=5888 miss=144      (non-streaming)
  prompt_tokens_details={'cached_tokens': 5888}          (streaming)

Test: TestOpenCodeSessionIsStableForCache asserts the session is stable
across requests for one source while the request id differs.

cmd/gui/package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "modelrouter-gui",
-  "version": "1.5.4",
+  "version": "1.5.6",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "modelrouter-gui",
-      "version": "1.5.4",
+      "version": "1.5.6",
       "license": "Proprietary",
       "devDependencies": {
         "electron": "^33.0.0",

cmd/gui/package.json

@@ -1,6 +1,6 @@
 {
   "name": "modelrouter-gui",
-  "version": "1.5.4",
+  "version": "1.5.6",
   "description": "ModelRouter Desktop — embedded ModelRouter core with tray",
   "author": "ModelRouter",
   "main": "main.js",

internal/lua/adapters/opencodego.lua

@@ -31,12 +31,20 @@ end
 
 function adapter.build_headers(meta)
     local ts = tostring(meta.timestamp or "")
+    local src = (meta.source and meta.source.name) or ""
     return {
         ["User-Agent"] = adapter.headers["User-Agent"],
         ["x-opencode-client"] = "cli",
         -- project 固定：同网关实例共享一个工作区身份
-        ["x-opencode-project"] = string.sub(sha256_hex("llmsproxy|" .. (meta.source and meta.source.name or "")), 1, 32),
+        ["x-opencode-project"] = string.sub(sha256_hex("llmsproxy|" .. src), 1, 32),
-        ["x-opencode-session"] = rand_id("ses_", "session|" .. ts),
+        -- session 必须**按源稳定**，不能每请求换：上游的前缀缓存在同一 session
+        -- 内才复用。实测（同一段 6032 token 提示词）：
+        --   固定 session  -> 第 2 次命中 5888/6032，cached_tokens=5888
+        --   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),
+        -- 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 "")),
     }
 end
@@ -79,6 +87,17 @@ function adapter.transform_request(raw_body)
             -- 上游直接 400（"The `reasoning_content` in the thinking mode must
             -- be passed back to the API"），agent 的每一轮都会失败。
             -- 注意：与 opencodezen.lua 的行为**相反**，不要在这里剥。
+            --
+            -- 但绝大多数客户端（pi 等）根本不保存也不回传 reasoning，只保留
+            -- 工具调用本身。上游只在“带 tool_calls 的助手轮”上校验这个字段，
+            -- 实测**空串即可通过校验**，所以缺省时补空串：既满足上游的
+            -- 一致性要求，又不伪造任何推理内容（用户看到的 reasoning 仍然是
+            -- 上游本轮真实返回的）。
+            if msg.role == "assistant"
+                and type(msg.tool_calls) == "table" and #msg.tool_calls > 0
+                and msg.reasoning_content == nil then
+                msg.reasoning_content = ""
+            end
             local drop = false
             if type(msg.content) == "table" then
                 local parts = {}

internal/lua/adapters/opencodezen.lua

@@ -32,12 +32,20 @@ end
 
 function adapter.build_headers(meta)
     local ts = tostring(meta.timestamp or "")
+    local src = (meta.source and meta.source.name) or ""
     return {
         ["User-Agent"] = adapter.headers["User-Agent"],
         ["x-opencode-client"] = "cli",
         -- project 固定：同网关实例共享一个工作区身份
-        ["x-opencode-project"] = string.sub(sha256_hex("llmsproxy|" .. (meta.source and meta.source.name or "")), 1, 32),
+        ["x-opencode-project"] = string.sub(sha256_hex("llmsproxy|" .. src), 1, 32),
-        ["x-opencode-session"] = rand_id("ses_", "session|" .. ts),
+        -- session 必须**按源稳定**，不能每请求换：上游的前缀缓存在同一 session
+        -- 内才复用。实测（同一段 6032 token 提示词）：
+        --   固定 session  -> 第 2 次命中 5888/6032，cached_tokens=5888
+        --   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),
+        -- 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 "")),
     }
 end

internal/lua/toolcall_preservation_test.go

@@ -194,6 +194,32 @@ func TestOpenCodeGoVsZenReasoning(t *testing.T) {
 		t.Errorf("opencodezen must still keep the tool call: %s", zout)
 	}
 
+	// An assistant turn that carries tool_calls but no reasoning_content must
+	// get an empty one injected: Go validates that field on tool-calling turns
+	// and 400s when it is absent, while most clients never send it.
+	// Verified against the live endpoint that an empty string passes.
+	bare := `{"model":"m","messages":[
+		{"role":"user","content":"go"},
+		{"role":"assistant","content":"","tool_calls":[{"id":"c1","type":"function","function":{"name":"read","arguments":"{}"}}]},
+		{"role":"tool","tool_call_id":"c1","content":"r"}
+	]}`
+	bout, err := vm.Transform("opencodego", "transform_request", bare)
+	if err != nil {
+		t.Fatalf("opencodego bare: %v", err)
+	}
+	if !strings.Contains(bout, `"reasoning_content":""`) {
+		t.Errorf("opencodego must inject an empty reasoning_content on a tool-calling turn: %s", bout)
+	}
+	// A plain assistant turn (no tool calls) must NOT gain the field.
+	plainAsst := `{"model":"m","messages":[{"role":"user","content":"hi"},{"role":"assistant","content":"hello"}]}`
+	pout, err := vm.Transform("opencodego", "transform_request", plainAsst)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if strings.Contains(pout, "reasoning_content") {
+		t.Errorf("opencodego must not inject reasoning_content on a plain assistant turn: %s", pout)
+	}
+
 	// Both must still omit stream_options on non-streaming requests.
 	for _, a := range []string{"opencodego", "opencodezen"} {
 		out, err := vm.Transform(a, "transform_request", `{"model":"m","messages":[{"role":"user","content":"hi"}]}`)
@@ -205,3 +231,53 @@ func TestOpenCodeGoVsZenReasoning(t *testing.T) {
 		}
 	}
 }
+
+// TestOpenCodeSessionIsStableForCache pins that the opencode client header set
+// keeps x-opencode-session STABLE per source while x-opencode-request stays
+// unique per call.
+//
+// Measured against the live OpenCode Go endpoint: the upstream prefix cache is
+// 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, so the cache could never hit.
+func TestOpenCodeSessionIsStableForCache(t *testing.T) {
+	for _, name := range []string{"opencodego", "opencodezen"} {
+		vm := NewVM(freshAdapterDir(t))
+		if err := vm.Start(); err != nil {
+			t.Fatal(err)
+		}
+
+		metaA := map[string]interface{}{
+			"timestamp": 1000,
+			"body":      `{"messages":[{"role":"user","content":"one"}]}`,
+			"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)
+		}
+		h2, err := vm.BuildHeaders(name, metaB)
+		if err != nil {
+			t.Fatalf("%s headers B: %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) — "+
+				"the upstream prefix cache is session-scoped, a rotating session kills every cache hit",
+				name, h1["x-opencode-session"], h2["x-opencode-session"])
+		}
+		if h1["x-opencode-request"] == h2["x-opencode-request"] {
+			t.Errorf("%s: x-opencode-request must differ per request", name)
+		}
+		vm.Stop()
+	}
+}