reasonix 0.3.0-alpha.1 → 0.3.0-alpha.2

package/README.md

@@ -94,22 +94,32 @@ with your own API key: `npx tsx benchmarks/tau-bench/runner.ts --repeats 3`.
 ### Extends to MCP (v0.3-alpha)
 
 Any [MCP](https://spec.modelcontextprotocol.io/) server's tools inherit
-the same Cache-First benefits. Live run with an MCP tool call in the
-middle of a conversation:
+the same Cache-First benefits. Two live runs, two data points:
 
-| turn | what happened | cache hit |
-|---|---|---:|
-| 1 | user asks, model decides to call `add` tool via MCP stdio | 0.0% (first-ever prefix) |
-| 1 (continued) | model receives tool result (42), writes final answer | **96.6%** |
+| server | turns | tool calls | cache hit | cost | vs Claude |
+|---|---:|---:|---:|---:|---:|
+| bundled demo (`add` / `echo` / `get_time`) | 2 | 1 | **96.6%** (turn 2) | $0.000254 | −94.0% |
+| official `@modelcontextprotocol/server-filesystem` | 5 | 4 | **96.7%** overall | $0.001235 | −97.0% |
 
-The MCP round-trip did not disturb the byte-stable prefix — server-side
-prompt cache kicked in on turn 2. Cost $0.000254 total, **94% cheaper
-than Claude** at equivalent token counts. Reference transcript:
-[`mcp-demo.add.jsonl`][mcp]. Reproduce:
+The second run is the interesting one — it's through an *external*,
+production MCP server (no code we control). Five turns including
+`list_directory`, a permission-denied recovery via
+`list_allowed_directories`, a successful retry, and `read_text_file`.
+Byte-stable prefix held across every turn; cache hit stayed at 96.7%.
+
+**Reproduce without an API key** (replay the committed transcripts):
+
+```bash
+npx reasonix replay benchmarks/tau-bench/transcripts/mcp-demo.add.jsonl
+npx reasonix replay benchmarks/tau-bench/transcripts/mcp-filesystem.jsonl
+```
+
+**Reproduce with your own key** (live, ~$0.002):
 
 ```bash
 reasonix chat --mcp "node --import tsx examples/mcp-server-demo.ts"
-# ask "use add to compute 17 + 25" — model calls the MCP tool, cache holds
+# or against the real filesystem server:
+reasonix chat --mcp "npx -y @modelcontextprotocol/server-filesystem /path/to/safe/dir"
 ```
 
 [mcp]: ./benchmarks/tau-bench/transcripts/mcp-demo.add.jsonl

package/dist/cli/index.js

@@ -2004,11 +2004,25 @@ var StdioTransport = class {
   stdoutBuffer = "";
   constructor(opts) {
     const env = opts.replaceEnv ? { ...opts.env ?? {} } : { ...process.env, ...opts.env ?? {} };
-    this.child = spawn(opts.command, opts.args ?? [], {
-      env,
-      cwd: opts.cwd,
-      stdio: ["pipe", "pipe", "inherit"]
-    });
+    const shell = opts.shell ?? process.platform === "win32";
+    if (shell) {
+      const line = [
+        opts.command,
+        ...(opts.args ?? []).map((a) => quoteArg(a, process.platform === "win32"))
+      ].join(" ");
+      this.child = spawn(line, [], {
+        env,
+        cwd: opts.cwd,
+        stdio: ["pipe", "pipe", "inherit"],
+        shell: true
+      });
+    } else {
+      this.child = spawn(opts.command, opts.args ?? [], {
+        env,
+        cwd: opts.cwd,
+        stdio: ["pipe", "pipe", "inherit"]
+      });
+    }
     this.child.stdout.setEncoding("utf8");
     this.child.stdout.on("data", (chunk) => this.onStdout(chunk));
     this.child.on("close", () => this.onClose());
@@ -2082,6 +2096,12 @@ var StdioTransport = class {
     else this.queue.push(msg);
   }
 };
+function quoteArg(s, windows) {
+  if (!windows) {
+    return `'${s.replace(/'/g, "'\\''")}'`;
+  }
+  return `"${s.replace(/"/g, '""')}"`;
+}
 
 // src/mcp/registry.ts
 async function bridgeMcpTools(client, opts = {}) {
@@ -2166,7 +2186,7 @@ function redactKey(key) {
 }
 
 // src/index.ts
-var VERSION = "0.3.0-alpha.1";
+var VERSION = "0.3.0-alpha.2";
 
 // src/cli/commands/chat.tsx
 import { render } from "ink";