# v0.4.66 (2026-05-29)

## Features
- Add Qoder provider: device-flow OAuth, COSY signing, WAF-bypass body encoding, live model catalog, dashboard quota tracker, 11 models (#1372)
- Add new models: Claude Opus 4.8 (Claude Code), GPT 5.4 Mini (Codex)

## Fixes
- DeepSeek thinking mode: echo `reasoning_content` back on follow-up/tool-call turns so OpenCode-free and custom providers no longer 400 with "reasoning_content must be passed back" (#1543)
- Reasoning injector: match deepseek/kimi model ids case-insensitively (covers custom providers using capitalized model names)
- OpenCode suggested-models: include free models without the `-free` suffix, e.g. `big-pickle` (#1535)

## Improvements
- Codex: trim sunset models, keep gpt-5.5 / gpt-5.4 / gpt-5.3-codex family, add gpt-5.4-mini
- volcengine-ark: refresh model list (add DeepSeek-V4-Flash/Pro, drop EOL entries)
- Lower stream stall timeout 35s → 30s for faster hang detection

CHANGELOG.md

@@ -1,3 +1,19 @@
+# v0.4.66 (2026-05-29)
+
+## Features
+- Add Qoder provider: device-flow OAuth, COSY signing, WAF-bypass body encoding, live model catalog, dashboard quota tracker, 11 models (#1372)
+- Add new models: Claude Opus 4.8 (Claude Code), GPT 5.4 Mini (Codex)
+
+## Fixes
+- DeepSeek thinking mode: echo `reasoning_content` back on follow-up/tool-call turns so OpenCode-free and custom providers no longer 400 with "reasoning_content must be passed back" (#1543)
+- Reasoning injector: match deepseek/kimi model ids case-insensitively (covers custom providers using capitalized model names)
+- OpenCode suggested-models: include free models without the `-free` suffix, e.g. `big-pickle` (#1535)
+
+## Improvements
+- Codex: trim sunset models, keep gpt-5.5 / gpt-5.4 / gpt-5.3-codex family, add gpt-5.4-mini
+- volcengine-ark: refresh model list (add DeepSeek-V4-Flash/Pro, drop EOL entries)
+- Lower stream stall timeout 35s → 30s for faster hang detection
+
 # v0.4.63 (2026-05-26)
 
 ## Fixes

cli/package.json

@@ -1,6 +1,6 @@
 {
   "name": "9router",
-  "version": "0.4.63",
+  "version": "0.4.66",
   "description": "9Router CLI - Start and manage 9Router server",
   "bin": {
     "9router": "./cli.js"

open-sse/config/runtimeConfig.js

@@ -32,7 +32,7 @@ export const MEMORY_CONFIG = {
 };
 
 // Stream stall timeout: abort if no chunk received within this duration
-export const STREAM_STALL_TIMEOUT_MS = 35 * 1000;
+export const STREAM_STALL_TIMEOUT_MS = 30 * 1000;
 
 // Fetch connect timeout: abort if upstream doesn't return response headers within this duration
 export const FETCH_CONNECT_TIMEOUT_MS = 20 * 1000;

open-sse/executors/opencode.js

@@ -1,14 +1,19 @@
 import { BaseExecutor } from "./base.js";
 import { PROVIDERS } from "../config/providers.js";
+import { injectReasoningContent } from "../utils/reasoningContentInjector.js";
 
 // Models that use /zen/v1/messages (claude format)
-const MESSAGES_MODELS = new Set(["big-pickle"]);
+const MESSAGES_MODELS = new Set();
 
 export class OpenCodeExecutor extends BaseExecutor {
   constructor() {
     super("opencode", PROVIDERS.opencode);
   }
 
+  transformRequest(model, body) {
+    return injectReasoningContent({ provider: this.provider, model, body });
+  }
+
   buildUrl(model) {
     const base = "https://opencode.ai";
     return MESSAGES_MODELS.has(model)

open-sse/utils/reasoningContentInjector.js

@@ -11,8 +11,8 @@ const PROVIDER_RULES = {
 
 // Model-level rules: matched by predicate against model id
 const MODEL_RULES = [
-  { match: m => m?.startsWith?.("kimi-"), scope: "toolCalls" },
+  { match: m => /^kimi-/i.test(m || ""), scope: "toolCalls" },
-  { match: m => m?.startsWith?.("deepseek-"), scope: "all" }
+  { match: m => /deepseek/i.test(m || ""), scope: "all" }
 ];
 
 const DEEPSEEK_V4_PRO = "deepseek-v4-pro";

tests/unit/reasoningContentInjector.test.js

@@ -0,0 +1,97 @@
+/**
+ * Unit tests for reasoningContentInjector (issue #1543).
+ *
+ * DeepSeek V4 thinking mode rejects follow-up requests whose assistant
+ * messages omit `reasoning_content` ("The `reasoning_content` in the thinking
+ * mode must be passed back to the API."). OpenAI-format clients strip it, so
+ * the injector echoes a placeholder back. These tests lock that behavior and
+ * guard that the OpenCode executor (which routes deepseek-v4-flash-free)
+ * actually runs the injector.
+ */
+
+import { describe, it, expect } from "vitest";
+import { injectReasoningContent } from "../../open-sse/utils/reasoningContentInjector.js";
+import { OpenCodeExecutor } from "../../open-sse/executors/opencode.js";
+
+const assistantWithToolCall = {
+  role: "assistant",
+  content: "",
+  tool_calls: [{ id: "call_x", type: "function", function: { name: "get_weather", arguments: "{}" } }],
+};
+
+function bodyWith(messages) {
+  return { model: "deepseek-v4-flash", messages, reasoning_effort: "medium" };
+}
+
+describe("injectReasoningContent — DeepSeek thinking round-trip", () => {
+  it("injects reasoning_content on a deepseek- assistant message that lacks it", () => {
+    const out = injectReasoningContent({
+      provider: "opencode",
+      model: "deepseek-v4-flash-free",
+      body: bodyWith([{ role: "user", content: "hi" }, assistantWithToolCall]),
+    });
+    const assistant = out.messages.find((m) => m.role === "assistant");
+    expect(typeof assistant.reasoning_content).toBe("string");
+    expect(assistant.reasoning_content.length).toBeGreaterThan(0);
+  });
+
+  it("preserves an existing reasoning_content instead of overwriting it", () => {
+    const original = "model's real chain of thought";
+    const out = injectReasoningContent({
+      provider: "opencode",
+      model: "deepseek-v4-flash-free",
+      body: bodyWith([{ ...assistantWithToolCall, reasoning_content: original }]),
+    });
+    expect(out.messages[0].reasoning_content).toBe(original);
+  });
+
+  it("applies provider-level rule for provider 'deepseek' (scope all)", () => {
+    const out = injectReasoningContent({
+      provider: "deepseek",
+      model: "deepseek-chat",
+      body: bodyWith([{ role: "assistant", content: "answer" }]),
+    });
+    expect(out.messages[0].reasoning_content).toBeDefined();
+  });
+
+  it("matches deepseek model id case-insensitively for custom providers (#1543)", () => {
+    const out = injectReasoningContent({
+      provider: "openai-compatible-custom",
+      model: "DeepSeek-V4-Flash",
+      body: bodyWith([assistantWithToolCall]),
+    });
+    expect(out.messages[0].reasoning_content).toBeDefined();
+  });
+
+  it("does not touch non-deepseek providers/models", () => {
+    const out = injectReasoningContent({
+      provider: "openai",
+      model: "gpt-5.5",
+      body: bodyWith([{ role: "assistant", content: "answer" }]),
+    });
+    expect(out.messages[0].reasoning_content).toBeUndefined();
+  });
+
+  it("maps deepseek-v4-pro-none alias to disabled thinking and strips reasoning_effort", () => {
+    const out = injectReasoningContent({
+      provider: "deepseek",
+      model: "deepseek-v4-pro-none",
+      body: bodyWith([{ role: "user", content: "hi" }]),
+    });
+    expect(out.model).toBe("deepseek-v4-pro");
+    expect(out.extra_body.thinking.type).toBe("disabled");
+    expect(out.reasoning_effort).toBeUndefined();
+  });
+});
+
+describe("OpenCodeExecutor — issue #1543 regression", () => {
+  it("runs the injector so deepseek-v4-flash-free round-trips reasoning_content", () => {
+    const executor = new OpenCodeExecutor();
+    const out = executor.transformRequest(
+      "deepseek-v4-flash-free",
+      bodyWith([{ role: "user", content: "hi" }, assistantWithToolCall]),
+    );
+    const assistant = out.messages.find((m) => m.role === "assistant");
+    expect(assistant.reasoning_content).toBeDefined();
+  });
+});