Repository navigation
KEYCLOAK-2940 - draft - Backchannel Logout - #7272
Conversation
b99d4f0 to
fe222ac
Compare
|
Haven't looked at this, and hoping @pedroigor can do so soon. With regards to "Why should we deprecate the old logout endpoint? The current GET logout will stay as it is, right?" - do you mean the RP initiated logout endpoint? There are improvements/changes we need to do there, but that is a separate issue to backchannel logout. |
Hey @stianst, yes in the Ticket: https://issues.redhat.com/browse/KEYCLOAK-2940?_sscc=t there it is written down that we should mark the old logout endpoint as deprecated. We asked ourselves if we should deprecate the old logout endpoint in our contribution and integrate the existing @get part into our new LogoutEndpoint or if we should leave it as it is so our contribution doesn't get to extensive. Greetings David |
|
@DaSmoo Reviewing this one today ... |
There was a problem hiding this comment.
Nice work, tks for this one. A few initial comments as a start so we can move forward depending on what you think about my comments. Basically:
- Do not change DDL but re-use client attributes to store logout metadata. See comment.
- A bit of nitpicking, so you could potentially revert changes that are basically changing formating.
Depending on whether or not you think my comments make sense, we should be able to reduce the size of the changeset.
I would also keep the current one and deal with it later. |
fe222ac to
9b7cee0
Compare
|
Hi @pedroigor, thanks for your feedback. We changed the PR according to your comments. We still have an issue with the cross dc tests running on Travis CI. Do you have an idea why these tests are failing (Maybe not needed anymore since now they seem to work out)? Maybe an other question about the review process. Should we have exactly one commit for this PR all the time or would you rather have us do multiple commits such that you see what we actually changed during the review process? Before finally merging we could still squash all the commits. Kind regards |
|
@benjamin37 Thanks for the latest changes. Cross-DC tests are unstable, so don't worry about it. But I'm going to check how the clustering ones (single dc) are doing. Regarding squashing commits, whatever you prefer. I like to go over the files again though, it helps me to understand more about the changes as well as catching anything I missed before :) |
You can ignore updating the logout endpoint as part of this, we'll handle that as a separate issue. Take a look at https://issues.redhat.com/browse/KEYCLOAK-11603 for more details |
|
@benjamin37 Only a few last comments. Also, it would be nice if we could have a better response to a backchannel logout when logout was not successful for some clients. Like a JSON listing the clients that were not successful, or something like that. But I think this is an improvement and not a blocker. |
|
@DaSmoo Need a rebase. Please, let me know when you have the updates we discussed. |
|
Hi @pedroigor, sorry for the delay. We'll provide the updates and the rebase tomorrow. |
e9c3444 to
626c753
Compare
|
Hi @pedroigor, we updated the PR. We'll also provide tests for downstream logouts, hope I can finish these ones today (or at least this week). |
|
@DaSmoo Np. Latest changes look good. |
|
Hi @pedroigor, we added the tests for downstream logouts, you can have an other look. |
|
@DaSmoo Could you rebase, please? Just noticed, after approving, that there are conflicts. |
|
@pedroigor sure, I'll rebase again |
|
@benjamin37 Forgot about something ... Could you also add this pedroigor@24e31b9 to your change set ? I know it is not something you did, but we should fix that part so that we can release connection properly. |
…onfigured <!--- Please read https://github.com/keycloak/keycloak/blob/master/CONTRIBUTING.md and follow these guidelines when contributing to Keycloak -->
…ogoutEndpoint <!--- Please read https://github.com/keycloak/keycloak/blob/master/CONTRIBUTING.md and follow these guidelines when contributing to Keycloak --> reorganized the backchannel endpoint to the current logoutEndpoint
…ogoutEndpoint <!--- Please read https://github.com/keycloak/keycloak/blob/master/CONTRIBUTING.md and follow these guidelines when contributing to Keycloak --> reorganized the backchannel endpoint to the current logoutEndpoint
<!--- Please read https://github.com/keycloak/keycloak/blob/master/CONTRIBUTING.md and follow these guidelines when contributing to Keycloak --> added Response as return type from the backchannel logout
4da17ee to
ca53549
Compare
|
@pedroigor did the rebase and integrated the changes of commit pedroigor@24e31b9 |
|
@benjamin37 Tks. Once CI finishes I'll merge. |
|
Hi @pedroigor, just wanted to ask if there is anything else we should do that' blocking the merge? |
|
@benjamin37 Merged, thanks ! |
* KEYCLOAK-2940 Backchannel Logout Co-authored-by: Benjamin Weimer <external.Benjamin.Weimer@bosch-si.com> Co-authored-by: David Hellwig <hed4be@bosch.com>
| return client.execute(post); | ||
| } | ||
|
|
||
| public CloseableHttpResponse doBackchannelLogout(String logoutTokon) { |
There was a problem hiding this comment.
There is a typo here. It was meant to be logoutToken instead of logoutTokon.
Hello,
we tried to implement the back-channel logout like it's described in the opendID specification. We would like to get technical feedback.
Open Points from our side:
OpenId Backchannel logout Spec: https://openid.net/specs/openid-connect-backchannel-1_0.html
RedHat ticket: https://issues.redhat.com/browse/KEYCLOAK-2940?_sscc=t