Hi Dapeng and all, I am just back from vacation and have been catching up on this thread. First, I'd like to express my strong interest in this topic. The problem of enabling fine-grained authorization, especially in the context of AI agents, is both timely and critical. This resonates with us as our team has also been exploring this space and has some early draft work on potential solutions, this was the primary focus of the side meetings we organized during both IETF 125 and 126. After reading through the discussion, my impression is that while the interest is high, the conversation is quickly becoming complex due to the introduction of various solution-specific terms and concepts. It feels a bit like we are all promoting our own approaches, which, while valuable, might be premature and risks making the problem space seem more fragmented than it needs to be at this early stage. To that end, I'd like to echo the sentiment that our primary focus should be on clearly defining the problem before diving into solutions. I believe it would be highly beneficial for the working group to first seek consensus on some foundational questions. For example: What is the core problem we are solving with "fine-grained authorization"? Is it primarily about adding a secondary, structured layer to the existing scope parameter (e.g., scope="transaction:create(amount<100,currency=USD)")? Or does it require defining an entirely new, dynamic authorization process that goes beyond static string matching? What is the architectural impact on OAuth 2.0? Can this be accomplished entirely within the existing OAuth 2.0 architecture (Client, AS, RS, Resource Owner)? Does it necessitate the introduction of new entities (e.g., a Policy Engine, an Agent Supervisor) or new elements (e.g., new grant types, new token formats, new endpoints)? Or, are we looking at a problem that might require a fundamentally new authorization architecture that sits alongside or builds on top of OAuth 2.0? Clarifying these high-level questions would help us establish a common ground and a clear charter for any future work, whether it's for a design team or for evaluating specific drafts. It would ensure we are all trying to solve the same, well-understood problem. Looking forward to the discussion at IETF 127. Best regards,
[email protected] 发件人： 刘大鹏(鹏成) 发送时间： 2026-10-02 05:11 收件人： Lombardo, Jeff; Yaron ZEHAVI; Ron Bartor; Karl McGuinness 抄送： [email protected]; Iman Schrock 主题： [OAUTH-WG]回复：Re: Call for interest: fine-grained authorization in OAuth (IETF 126 follow-up) Hi Jeff and all, I think whether the problem is real and whether there is enough interest in the WG to work on it are separate from the question of which draft would be the solution. That was the purpose of the call for interest, and I read the replies so far as interest in the problem itself rather than in any particular solution. The discussion in this thread reaches a similar problem from several independent directions. We reached it ourselves earlier: draft-liu-agent-operation-authorization was presented at IETF 125. It investigates how to extend OAuth to express bounded work proposals from agents and the mechanism for approving them. It shares much of the problem and solution space discussed in this thread. I think the important question for the next steps and for the upcoming IETF 127 meeting is whether the WG has enough support for the problem space and enough interest to work on potential solutions. We do not need to limit ourselves to a specific draft at this stage. If we agree on the problem, the WG or a design team can work on the solution together. Regards, Dapeng ------------------原始邮件 ------------------ 发件人:Lombardo, Jeff <[email protected]> 发送时间:Thu Oct 1 23:47:20 2026 收件人:Yaron ZEHAVI <[email protected]>, Ron Bartor <[email protected]>, Karl McGuinness <[email protected]> 抄送:[email protected] <[email protected]>, Iman Schrock <[email protected]> 主题:[OAUTH-WG] Re: Call for interest: fine-grained authorization in OAuth (IETF 126 follow-up) Agreed with Yaron, I thought I provided the reference. It seems not. @Ron : The discussion is the right one, it just that I think we should have it as part of the Mission Draft instead of yet another Draft. Jeff Jean-François “Jeff” Lombardo |Amazon Web Services Principal Standards Specialist, Identity Services Montréal, Canada From: Yaron ZEHAVI <[email protected]> Sent: October 1, 2026 1:43 AM To: Ron Bartor <[email protected]>; Karl McGuinness <[email protected]> Cc: Lombardo, Jeff <[email protected]>; [email protected]; Iman Schrock <[email protected]> Subject: RE: [EXT] [OAUTH-WG] Re: Call for interest: fine-grained authorization in OAuth (IETF 126 follow-up) CAUTION: This email originated from outside of the organization. Do not click links or open attachments unless you can confirm the sender and know the content is safe. AVERTISSEMENT: Ce courrier électronique provient d’un expéditeur externe. Ne cliquez sur aucun lien et n’ouvrez aucune pièce jointe si vous ne pouvez pas confirmer l’identité de l’expéditeur et si vous n’êtes pas certain que le contenu ne présente aucun risque. Dear Ron, I think the goal enforcement you’re seeking may be found in@Karl McGuinness’s draft:Mission-Bound Authorization for OAuth 2.0. It adds an AS-persisted durable higher level mission intent object, against which authority requests are evaluated at token issuance time. It should empower the authorization server to evaluate if reservation A and payment B are within the scope of the approved mission, apply policies to validate they’re related and if so issue the tokens for the relevant audience resource servers. Regards, Yaron Classification: GENERAL From: Ron Bartor <[email protected]> Sent: Thursday, October 1, 2026 3:58 AM To: Yaron ZEHAVI <[email protected]> Cc: Lombardo, Jeff <[email protected]>;[email protected]; Iman Schrock <[email protected]> Subject: Re: [OAUTH-WG] Re: Call for interest: fine-grained authorization in OAuth (IETF 126 follow-up) You don't often get email [email protected]. Learn why this is important This message is from an external sender - be cautious, particularly with links and attachments. Hi Jeff, Yaron, Yaron, thanks for the correction, and good to meet you. I was citing the old draft, my mistake. I'll cite draft-ietf-oauth-rar-metadata-remediation from here on and stop saying "per-RS discovery", since that's not what it does. The way I read it now, the metadata endpoint tells a client what the AS can issue, and what a particular resource actually needs you find out by calling it and getting the remediation back. I also take the gateway point. It relays the call and relays the remediation and doesn't need to know anything about the downstream types to do that. Jeff, agreed on the rest. Each RS says what it needs in RAR terms, the AS normalizes, and if there's a broker in front it adds one more layer and normalizes for its own client. That's the per-RS problem, and I think the draft handles it well. My write-up says as much. What I'm trying to point at is one step above that, and a concrete case is clearer than my first mail was. Say the goal is "buy product A". It turns into a reservation at an inventory service and a charge at a payments service (two RSs with their own vocabularies, and quite possibly two different ASs). Each RS remediates in its own terms, each remediation gets normalized correctly, each request gets authorized. Except the reservation is for A and the charge is for B. Nothing in that path compares the two, and I don't think anything in it can, because comparing them needs the goal, and the AS that has authority over the payments service doesn't hold the goal. It holds a grant for one service, not what the user was trying to do across several. Yaron's correction actually makes this a bit sharper. If there's no discovery ahead of time, whoever holds the goal can't decompose it into typed parts up front. It only learns what each RS needs when that RS refuses. So the question "is this remediation still within the goal" has to be asked on every remediation as it comes back, and then once more across all of them at the end. The gateway relays those without reading them, which is the right thing for a gateway. But somebody still has to read them against the goal, and that's the party I'd like the design team to name, whether it ends up being the client, the AS, the broker, or each RS for its own slice. If the answer is "the broker, when there is one", fine, that's an answer, but I'd rather it was said out loud, because it means the goal, and whatever evidence is needed to judge against it, lives at the intermediary. Jeff, I think your token exchange idea fits here. If an exchange can hand back a RAR remediation, the broker gets a typed remediation at token time, in the RS's own vocabulary, without having to be refused by the RS first. For the per-RS half of this across a broker hop that's probably the cleanest carrier, and I'll put it in the write-up next to ID-JAG. Ron On Wed, 30 Sept 2026 at 08:18, Yaron ZEHAVI <[email protected]> wrote: Hello everyone, @Lombardo, Jeff thanks for the shout out. @Ron Bartor, pleased to meet you One comment, OAuth 2.0 RAR Metadata and Error Remediation does not offer per-RS metadata discovery. This idea was explored in earlier drafts: https://www.ietf.org/archive/id/draft-zehavi-oauth-rar-metadata-03.html#name-oauth-20-protected-resource And removed following feedback from WG members. The idea was add to RFC 9728 RS metadata: "authorization_details_types_required": { "oneOf": ["payment_initiation", "payment_approval", "beneficiary_designation"] } With Boolean expressions allOf, and, or. This was deemed not very helpful as: Different resources have different requirements (but in MCP the resource is not expressed on the http path) Lots of logic which in the end doesn’t tell the client exactly which RAR types to request. Then the next idea was include the Boolean logic in the WWW-Authenticate header. Opted instead to return the actionable RAR object to remediate the failure. That being said, I think the task of RS-Gateways was made simpler. They don’t need to have foreknowledge to combine downstream RS metadata. Instead, client makes a request, a failing downstream RS may return the remediation payload. Gateway relays the calls without requiring additional metadata. Yaron Classification: GENERAL From: Lombardo, Jeff <[email protected]> Sent: Wednesday, September 30, 2026 4:08 PM To: Ron Bartor <[email protected]> Cc: [email protected]; Yaron ZEHAVI <[email protected]>; Iman Schrock <[email protected]>; Lombardo, Jeff <[email protected]> Subject: RE: [OAUTH-WG] Re: Call for interest: fine-grained authorization in OAuth (IETF 126 follow-up) This message is from an external sender - be cautious, particularly with links and attachments. Hi Ron, Speaking under the supervision of Yaron. I am not sure I follow the multi-RS decomposition problem you try to point at here. draft-zehavi-oauth-rar-metadata now draft-ietf-oauth-rar-metadata-remediation [https://datatracker.ietf.org/doc/draft-ietf-oauth-rar-metadata-remediation/] allows each RS to express the RAR-based mediated response along what the AS that has authority can speak in terms of RAR schema. It means that it is up to each AS to normalize the mediated response, If brokered through an API Gateway, this is just adding another layer and it is now up to the Gateway / Broker to normalize it for its client. As ID-JAG supports RAR, there could be an extension to Token Exchange to return a RAR remediation to ease this path. Jeff Jean-François “Jeff” Lombardo |Amazon Web Services Principal Standards Specialist, Identity Services Montréal, Canada From: Ron Bartor <[email protected]> Sent: September 29, 2026 7:09 PM To: Iman Schrock <[email protected]> Cc: [email protected] Subject: [EXT] [OAUTH-WG] Re: Call for interest: fine-grained authorization in OAuth (IETF 126 follow-up) CAUTION: This email originated from outside of the organization. Do not click links or open attachments unless you can confirm the sender and know the content is safe. AVERTISSEMENT: Ce courrier électronique provient d’un expéditeur externe. Ne cliquez sur aucun lien et n’ouvrez aucune pièce jointe si vous ne pouvez pas confirmer l’identité de l’expéditeur et si vous n’êtes pas certain que le contenu ne présente aucun risque. Hi Dapeng, all, I support continuing this direction and would like to contribute to the design team. I wasn't in the room at 126, so apologies if this was covered, but I'd like to put one scenario on the table for the "goal state management" and "discoverable schema" pillars. I operate an enterprise API gateway that fronts MCP and agent traffic. A single agent request routinely fans out to several downstream resource servers, and each of those RSs owns its own authorization semantics: its own notion of what a task is, what the constraining attributes are, and how a request is scoped. Those semantics are not shared across services, and in some cases cannot be. A concrete example is an RS that was integrated from a separate business unit; its authorization model reflects its own history and is materially different from the rest of our services, and harmonizing it is neither quick nor, for some of its consumers, desirable. In that setting, per-RS schema discovery (as in draft-zehavi-oauth-rar-metadata) solves the local problem but not the cross-RS one: the goal has to be carried across trust domains that are mutually opaque, and something has to decide whether each downstream task is still within the goal without any RS seeing the others' vocabulary. The slides put "task in goal" evaluation out of scope, which I understand, but I think the design team should at least be explicit about where that evaluation lives in a multi-RS decomposition (client, AS, gateway/intermediary, or each RS independently) and what the goal-state representation needs to look like so that it remains meaningful to an RS that only understands its own schema. I'd be glad to write this up as a concrete use case, and I think it fits naturally with the RS-to-client signaling work already in the WG (txn-challenge, client-challenge, RAR-metadata) rather than requiring new machinery. Best regards, Ron Bar-Tor On Tue, Sep 29, 2026 at 3:13 PM Iman Schrock <[email protected]> wrote: Hi Dapeng, I support continuing this work. One boundary I would like the design team to test: a goal-level authorization can help a client negotiate what an RS requires, but it is not approval of the eventual exact action. A changed payment destination after negotiation, or a lost response after provider entry, needs its own decision and recovery rule. We have published AEB and an open vector pack for that boundary. I would be glad to bring a small cross-system case to the design team and see where it belongs alongside existing OAuth work. Best, Iman On Wed, 30 Sep 2026 00:19:52 +0800, "刘大鹏(鹏成)" <[email protected]> wrote: Hello all, During IETF 126 we had a discussion on how OAuth can support fine-grained authorization for AI agents [1]. The topic generated a lot of interest in the room, and the poll showed support for continuing the discussion [2]. A quick summary of the problem space as presented in the session [3]: 1. Enabling clients to construct fine-grained authorization requests using: a. Goal state management, b. Discoverable domain-specific schemas for task and authorization definition, c. Task-in-goal evaluation requests 2. Establishing a negotiation pattern that allows a resource server to guide clients towards the required authorization The session also proposed forming a design team to explore this space [3]. Before IETF 127, we would like to hear from the WG: - Is this a direction the community is interested in pursuing? Replies on the list will help shape the discussion at IETF 127. [1]https://datatracker.ietf.org/meeting/126/materials/minutes-126-oauth-202607240700-00 [2]https://datatracker.ietf.org/doc/polls-126-oauth-202607240900/ [3] https://datatracker.ietf.org/meeting/126/materials/slides-126-oauth-sessb-policy-language-binding-for-oauth-00 Best regards,Dapeng Liu _______________________________________________ OAuth mailing list -- [email protected] To unsubscribe send an email to [email protected] This message and any attachment ("the Message") are confidential. If you have received the Message in error, please notify the sender immediately and delete the Message from your system, any use of the Message is forbidden. Correspondence via e-mail is primarily for information purposes. RBI neither makes nor accepts legally binding statements via e-mail unless explicitly agreed otherwise. Information pursuant to § 14 Austrian Companies Code: Raiffeisen Bank International AG; Registered Office: Am Stadtpark 9, 1030 Vienna, Austria; Company Register Number: FN 122119m at the Commercial Court of Vienna (Handelsgericht Wien). This message and any attachment ("the Message") are confidential. If you have received the Message in error, please notify the sender immediately and delete the Message from your system, any use of the Message is forbidden. Correspondence via e-mail is primarily for information purposes. RBI neither makes nor accepts legally binding statements via e-mail unless explicitly agreed otherwise. Information pursuant to § 14 Austrian Companies Code: Raiffeisen Bank International AG; Registered Office: Am Stadtpark 9, 1030 Vienna, Austria; Company Register Number: FN 122119m at the Commercial Court of Vienna (Handelsgericht Wien).
_______________________________________________ OAuth mailing list -- [email protected] To unsubscribe send an email to [email protected]
