fix(fable-mcp): fix send_message to use correct two-step API flow

POST .../messages to start generation, then stream from .../generation/stream.
The previous implementation used a non-existent /stream endpoint.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

fable-mcp/fable_mcp/tools/chat.py

@@ -28,7 +28,8 @@ async def send_message(
     """Send a message to Fable and return the full assistant response.
 
     Creates a new MCP conversation if conversation_id is None.
-    Streams the SSE response and accumulates token chunks into a single string.
+    Posts the user message to start generation, then streams the SSE buffer
+    and accumulates token chunks into a single string.
 
     Returns:
         Dict with:
@@ -41,18 +42,19 @@ async def send_message(
             "/api/chat/conversations",
             json={"conversation_type": "mcp"},
         )
-        conversation_id = conv["id"]
+        conversation_id = str(conv["id"])
 
-    # Build SSE stream URL with message as query param
-    params: dict[str, Any] = {"message": message}
-    if think:
-        params["think"] = "true"
+    # Start generation
+    await client.post(
+        f"/api/chat/conversations/{conversation_id}/messages",
+        json={"content": message, "think": think},
+    )
 
     tokens: list[str] = []
     tool_calls: list[Any] = []
 
-    stream_path = f"/api/chat/conversations/{conversation_id}/stream"
-    async for raw_line in client.stream_get(stream_path, params=params):
+    stream_path = f"/api/chat/conversations/{conversation_id}/generation/stream"
+    async for raw_line in client.stream_get(stream_path):
         if not raw_line.startswith("data: "):
             continue
         payload_str = raw_line[len("data: "):]

fable-mcp/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "fable-mcp"
-version = "0.2.1"
+version = "0.2.2"
 description = "MCP server for Fabled Assistant"
 requires-python = ">=3.12"
 dependencies = [