RE: Squid-2.5.STABLE?

> Chemolli Francesco (USI) wrote:
>
> > > You can't blaim the helpers for Squid not telling the helpers
> > > what the client
> > > is willing to negotiate.
> >
> > Squid _does_ tell the helpers what the client is willing to
> > negotiate. It's all in the NTLMSSP packet (the amorphous blob
> > squid sends to the helpers)
>
> Err... the negotiation is taking place during the "hello"
> packet exchange,
> where the protocol helper protocol only sends "TT\n". Due to
> this the only
> negotiation that can take place is that the Squid helper
> tells the client
> "irregardless of what you just said, I want this", and then
> the client can
> try to adjust to it.. Not much of a window for negotiation, is it?

Doh, you're right.
Bringing back to the ML, it might interest others.

The problem is not in the TT, but in the fact that
the "YR" packet doesn't send to the helper the original
negotiate request.

Accomodating for this will require some pretty heavy
infrastructure overhaul: auth-cache and challenge
reusal are going to be heavily affected (although not in
an irreparable way, I hope).

What's your take Robert?

-- 
	/kinkie