sference-cli 0.0.4__tar.gz → 0.0.5__tar.gz

{sference_cli-0.0.4 → sference_cli-0.0.5}/PKG-INFO

@@ -1,9 +1,9 @@
 Metadata-Version: 2.4
 Name: sference-cli
-Version: 0.0.4
+Version: 0.0.5
 Summary: sference command-line interface
 Requires-Python: >=3.12
-Requires-Dist: sference-sdk>=0.0.4
+Requires-Dist: sference-sdk>=0.0.5
 Requires-Dist: typer>=0.24.1
 Description-Content-Type: text/markdown
 

{sference_cli-0.0.4 → sference_cli-0.0.5}/pyproject.toml

@@ -1,12 +1,12 @@
 [project]
 name = "sference-cli"
-version = "0.0.4"
+version = "0.0.5"
 description = "sference command-line interface"
 readme = "README.md"
 requires-python = ">=3.12"
 dependencies = [
     "typer>=0.24.1",
-    "sference-sdk>=0.0.4",
+    "sference-sdk>=0.0.5",
 ]
 
 [project.scripts]

{sference_cli-0.0.4 → sference_cli-0.0.5}/sference_cli/main.py

@@ -300,6 +300,11 @@ def responses_create(
         "--include-reasoning/--no-include-reasoning",
         help="Include extracted reasoning in the response output (default: true).",
     ),
+    enable_thinking: bool | None = typer.Option(
+        None,
+        "--enable-thinking/--disable-thinking",
+        help="Qwen3: forward to tokenizer apply_chat_template. Omit for tokenizer default.",
+    ),
     wait: bool = typer.Option(False, "--wait/--no-wait"),
     poll_ms: int = typer.Option(500, "--poll-ms", help="Polling interval when --wait is enabled."),
     timeout_s: int = typer.Option(60, "--timeout-s", help="Timeout in seconds when --wait is enabled."),
@@ -312,6 +317,7 @@ def responses_create(
             model=model,
             input=[{"role": "user", "content": content}],
             include_reasoning=include_reasoning,
+            enable_thinking=enable_thinking,
         )
     )
     if wait: