- Schema:
agent-mediate/mechanism-spec/v1 - Rules Version (
RULES_VERSION):1.3.0 - Canonical Rules Hash (
RULES_HASH):8d7e67e1145097e3ce20d8828e451db20453d864782c91ccb08be2e9e613cdc4 - Machine-Readable Endpoint:
GET /v1/rules(sha256Hex(canonicalJson(spec)) === rulesHash)
Every platform-signed settlement instruction, UNRESOLVED certificate, transparency checkpoint, and co-signed agent-mediate/clause/v1 embeds rulesVersion and rulesHash (RFC 8785 JCS + SHA-256 over MECHANISM_SPEC). Any change to the deterministic rules, domains, clamping, distance metric, or window limits changes RULES_HASH and requires a RULES_VERSION bump.
1. Issue Grid, Linear Utility, and No-Retraction Monotonicity
A confirmed dispute defines 1 ≤ m ≤ 5 negotiable issues I = \i_1, …, i_m\. Each issue i has:
- Inclusive domain [i.min, i.max] with granularity i.step > 0, where (i.max - i.min) / i.step is an exact integer.
- Preference orientation i.claimantPrefers ∈ \"higher", "lower"\ (the respondent strictly prefers the opposite direction).
- Designated performer i.obligor ∈ \"claimant", "respondent"\.
Grid Alignment & Even-Half Rounding
Every package x ∈ ℝ^m submitted or output by the mechanism lies on the exact step grid x_i = i.min + k · i.step (k ∈ ℤ). Exact half-step midpoints snap to the even grid index k so rounding has zero directional bias toward claimant or respondent.
Normalised Share & Additive Utility
For value x_i ∈ [i.min, i.max], the claimant's normalised share is:
s_C(i, x_i) = (x_i - i.min) / (i.max - i.min) if i.claimantPrefers = "higher" (i.max - x_i) / (i.max - i.min) if i.claimantPrefers = "lower"
and the respondent's share is s_R(i, x_i) = 1 - s_C(i, x_i). Given a party p's confidential Round-1 non-negative weights w_p (\sum_i w_p,i = 1), party p's normalised utility is U_p(x) = \sum_i ∈ I w_p,i s_p(i, x_i) ∈ [0, 1].
Per-Issue No-Retraction Rule
In every bargaining round r > 1 (and in final-offer determination), each party's new offer x^(r) must concede or hold steady on every issue relative to its previous offer x^(r-1):
- Claimant: s_C(i, x^(r)_i) ≤ s_C(i, x^(r-1)_i) for all i ∈ I.
- Respondent: s_C(i, x^(r)_i) ≥ s_C(i, x^(r-1)_i) for all i ∈ I.
Violations are rejected immediately with 422 RETRACTION.
2. Principal-Signed Mandates and Confidential Inputs
Mandates (agent-mediate/mandate/v1)
Principals authorise agents via Ed25519-signed mandates specifying:
bounds: inclusive per-issue authority intervals [B_p,i^min, B_p,i^max] for voluntary bargaining (OVERLAP_MIDPOINT,PROPOSAL_ACCEPTED,SETTLEMENT_IMPROVED).- Optional
determinationConsent: trueand optionaldeterminationBounds(MECH-1,D126).determinationBoundsmay be tighter or wider than voluntarybounds, enabling two-tier mandates where principals pair cautious voluntary bargainingboundswith wider fallbackdeterminationBoundsso non-overlapping voluntary mandates can still resolve viaFINAL_OFFER_DETERMINATION. expiresAt(must outlivebargainingWallClockMs, plusdeterminationTimeoutMswhendeterminationConsentis enabled;MECH-5), monotonicissuedAton replacement (CR2-11), and optionalscope: { contractHash, counterpartyId }(H2).- When a co-signed pre-dispute
agent-mediate/clause/v1specifies non-emptyterms.issueTemplates,proposedIssuesat filing must be a non-empty subset matching each template'sid,claimantPrefers,obligor,unit, andstepwith on-grid[min, max]inside[template.min, template.max](422 CLAUSE_VIOLATIONon mismatch;SEC-2). Mutually confirmed AI trade-off suggestions duringISSUE_CONFIRMATIONremain permitted when both parties confirm with valid mandates.
Resolving Non-Overlapping Mandates (D126, D127)
When principals' initial single-issue or narrow mandates do not overlap (B_C ∩ B_R = ∅), three mechanism paths enable settlement without compromising principal control or Round-1 confidentiality:
- Adopting AI-Suggested Trade-Off Issues (
REJECT_ISSUES.adoptSuggestedIds): DuringISSUE_CONFIRMATION(whenproposalCount < maxIssueProposals), either party may callREJECT_ISSUESbound to the currentissuesHash(409 HASH_MISMATCHif stale,BUG-3) with optionaladoptSuggestedIds(1..2issue IDs fromadvisory.suggestedIssues). OmittingadoptSuggestedIdsresets the nextPROPOSE_ISSUEStofiling.proposedIssues; passingadoptSuggestedIdspreservesfiling.proposedIssues, consecutively adopted prior suggestions (priorAdoptedSuggestedIds), mutually mandated suggestions, and the newly adopted IDs (total <= 5, zero extra LLM calls), allowing both parties to callCONFIRM_ISSUESwith multi-issue replacement mandates and logroll across issues. - In-Place Monotonic Principal Escalation (
UPDATE_MANDATE): DuringBARGAININGorDETERMINATION, either party may submit up toMAX_MANDATE_UPDATES = 3replacement mandates (POST /v1/disputes/{id}/mandate), surfaced innextActionswhenever anopenProposalexceeds the party's current mandate (proposalWithinYourMandate === false), inDETERMINATION, or in single-issue rounds where standing offers remain disjoint. The replacement must come from the sameprincipalIdwith strictly newerissuedAt,next.expiresAt >= previous.expiresAt, identicaldeterminationConsent(determinationConsentis frozen onceBARGAININGopens so neither party can unilaterally flip determination opt-in after seeing bargaining dynamics,SEC-1), and raw + grid-clamped superset bounds (B'_p ⊇ B_p, plus D'_p ⊇ D_p whendeterminationConsentis enabled;BUG-1) covering Round-1declared.limitsand any standing/in-round offer. When both mandates consent to determination, bargaining offers must also stay withindeterminationBoundson every issue (BUG-7) so no party can concede past its determination authority during bargaining. Round-1private(weights,walkaway,limits) stays strictly frozen (M13/MECH-8);UPDATE_MANDATEappends an opaque"internal"MANDATE_REGISTEREDlink in/auditand redacts counterparty/signaturesrows toaction: "confidential_action"withagentId: null(SEC-1). - Two-Tier
determinationBounds: SettingdeterminationConsent: truewithdeterminationBoundswider than voluntaryboundsresolves deadlocked bargaining viaFINAL_OFFER_DETERMINATIONwithout manual escalation.
Round-1 Confidential Inputs (private)
With its first offer, each party submits private: { weights, walkaway, limits? }, frozen for the remainder of the dispute:
walkaway(W_p) must lie on the grid and insidemandate.bounds(MECH-5).- Optional
limits(L_p,i = [L_p,i^min, L_p,i^max]) restrict platform proposals and post-settlement Pareto improvements to a feasible sub-box containing W_p insidemandate.bounds(MECH-7). - Confidential inputs never enter any LLM prompt and never leave the submitting party's own
PartyView.
3. Crossing-Offer Settlement (OVERLAP_MIDPOINT, MECH-6)
When Round r closes with standing offers (O_C, O_R), offers cross if and only if each party's utility from the counterparty's offer meets or exceeds its utility from its own offer under its declared weights (for single-issue disputes, s_C(O_R) ≥ s_C(O_C)).
- Compute the per-issue grid-snapped midpoint M_i = snap_even(1/2(O_C,i + O_R,i)).
- If M lies inside both parties'
mandate.bounds, settle at M. - Otherwise (
MECH-6), clamp overflowing issues to the intersection box B_C ∩ B_R and greedily step compensating issues within B_C ∩ B_R on the step grid to minimise \max_p max(0, U_p(O_p) - U_p(x)) subject to U_C(x) ≥ U_C(O_C) and U_R(x) ≥ U_R(O_R) whenever feasible inside B_C ∩ B_R.
4. Single-Negotiating-Text Platform Proposals (PROPOSAL_ACCEPTED, MECH-7, D75, SEC3-5)
From proposalFromRound (default Round 2), the platform presents an openProposal every round:
Secret Pair-Keyed Split α ∈ [0.3, 0.7] & Creation-Time Commitments
- At filing, the platform derives
proposalKey = HMAC-SHA256(PROPOSAL_SECRET, "agent-mediate/proposal-key/v1\n" + sortedPair + "\n" + contractHash)(or, in unkeyed"salted"mode, the one-way per-disputeproposalSalt = SHA256(auditSalt + ":" + disputeId + ":proposal-split"), never rawaudit.salt,M8) and publishesproposalKeyCommitment = SHA256("agent-mediate/proposal-key-commit/v1\n" + disputeId + "\n" + mode + "\n" + keyOrSalt)inDISPUTE_FILEDbefore either party submits Round-1 confidential inputs (SEC3-5). - On Round-1 submission, each party p receives a personal 256-bit blinding salt
partySaltanddeclaredCommitment = SHA256("agent-mediate/declared-input-commit/v1\ncommit\n" + disputeId + "\n" + p + "\n" + partySalt + "\n" + canonicalJson(private_p)), anchored into the/audithash chain and recorded on the signed outcome document. - α ∈ [0.3, 0.7] (
E[\alpha] = 0.5) is derived deterministically viaHMAC-SHA256(proposalKey, "agent-mediate/proposal-split/v1\n" + canonicalJson(privates))in"keyed"mode (or fromproposalSaltin"salted"mode). Keeping α secret prevents a single party from inverting P = W_C + α(W_R - W_C) to recover the counterparty's low-entropy walkaway (H1). Because"keyed"proposalKeyis shared across disputes for(pair, contractHash), a live"keyed"proposalKeyis never disclosed to a disputing party (H5: doing so would break walkaway hiding in subsequent disputes between that pair);"keyed"verifyProposalOpening(bindingexpectedIssuesHash) is intended strictly for a confidentiality-bound independent auditor (or after rotatingPROPOSAL_SECRET), whereas"salted"mode opens only the per-disputeproposalSalt.
Constrained Asymmetric Nash Optimisation & Non-Interference Stand-Ins
- Let feasible box F = L_C ∩ L_R (defaulting omitted
limitsto [i.min, i.max]). - The platform runs a deterministic discrete search over the grid points of F for a package x with U_C(x) ≥ U_C(W_C) and U_R(x) ≥ U_R(W_R) (to within 10^-9). It solves the continuous linear frontier of F, then snaps the single fractional pivot issue to its floor and ceiling grid values and recursively re-optimises the remaining issues on each sub-box (
FS-H1). If the search finds such a package (settles = true), both parties see the visited package maximising:(U_C(x) - U_C(W_C))^α (U_R(x) - U_R(W_R))^1-α
(ties within 10^-9 break by smaller distance from the continuous pivot value, then by the even grid index of the pivot,FS-M4b). If both parties respond"accept"and x ∈ B_C ∩ B_R, the dispute settles withmethod: "PROPOSAL_ACCEPTED". - The search is best-effort, not exhaustive (D125,
CR-CORE-M1,CR-CORE-L5). On coarse multi-issue grids with a very narrow zone of agreement it can miss an on-grid package both parties would accept: about 0.1% of random 3-issue disputes that have such a package, and none of 20,000 random 2-issue disputes with strictly positive surplus. A miss is never a wrong settlement; it only means no settling proposal is shown that round (the parties see stand-ins, below), and bargaining, final-offer determination and every other guarantee continue unchanged. Note on historical verifiability (CR-CORE-L5): recursive multi-issue pivot snapping (FS-H1) and even-grid-index midpoint tie-breaking (FS-M4b) took effect on 2026-11-05 underRULES_VERSION = "1.1.0"; proposal openings (verifyProposalOpening) from pre-2026-11-05 multi-issue or odd-step disputes may differ on round proposals while their signed outcomes and audit chains remain valid. An exact, bounded branch-and-bound search is deferred to a future rules version, together with dual-version proposal verification. - If no mutually acceptable zone exists in F (
settles = false, never disclosed), each party p sees a deterministic reflected stand-in inside its own L_p at or above U_p(W_p) (CR2-2,D75). Accepting a stand-in behaves identically to a counterparty rejection, preserving strict non-interference across arbitrary counterparty walkaways.
5. Post-Settlement Pareto Frontier Improvement (MECH-10)
When a multi-issue dispute settles with EXECUTION_PENDING and strictly Pareto-superior packages x ∈ (B_C ∩ L_C) ∩ (B_R ∩ L_R) exist above the settled baseline T (U_C(x) ≥ U_C(T), U_R(x) ≥ U_R(T), with at least one strict inequality), the platform computes the symmetric (α = 0.5) Nash improvement over baseline T (never over secret walkaways W_p) and opens execution.improvement.
- Individual responses remain masked until resolved.
- If both parties submit
acceptbefore any execution proof is filed,SETTLEMENT_IMPROVEDupgrades the settled terms and records a new signed snapshot indispute_outcomes.
6. Stall Detection (MECH-3) and Wall-Clock Guard (MECH-4)
- Gap: gap_r = (1) / (m)\sum_i ∈ I max(0, s_C(i, O_C,i) - s_C(i, O_R,i)) ∈ [0, 1].
- Relative Progress (
MECH-3): Round r ≥ 2 makes progress when gap_r-1 - gap_r ≥ stallThreshold · gap_r-1 (defaultstallThreshold = 0.05overstallWindow = 2consecutive transitions). Using relative reduction avoids falseSTALLEDterminations when parties actively concede inside a narrow < 5\% gap. - Full-Window Guard (
MECH-4): Round r + 1 opens only if r < maxRounds and wallClockDeadline - now ≥ roundTimeoutMs.
7. Contractual Binding Final-Offer Determination (MECH-1, MECH-8)
Legal Character (D52): Contractual final-offer determination is an automated mathematical formula pre-agreed by both principals in signed mandates (determinationConsent: true), not statutory arbitration, adjudication, or an arbitral award.
When bargaining ends STALLED or NO_OVERLAP_AT_CAP and both active principal-signed mandates carry determinationConsent: true:
- Offer-Independent Reference (
MECH-8): The reference package R^* is computed solely from the frozen Round-1 declared inputs (declaredReferenceTerms: symmetric α = 0.5 Nash solution over L_C ∩ L_R when a zone exists, else per-issue grid midpoint of (W_C, W_R)). Conceding generously during bargaining never shifts R^* against the conceding party. - Final Offers & Mean-Weight Distance (
MECH-8): Each party may submit one final offer withindeterminationBounds(defaulting to its last bargaining offer if omitted). Offers are scored by mean-declared-weight normalised L_1 distance:d(O_p, R^*) = \sum_i ∈ I \fracw_C,i + w_R,i2 · \frac|O_p,i - R^*_i|i.max - i.min
preventing low-weight-issue sacrifice gaming. Exact ties break deterministically viaSHA256(auditSalt + ":" + disputeId + ":arbitration-tiebreak"). - Bilateral Mandate Gate (
MECH-1): The closer final offer settles asFINAL_OFFER_DETERMINATIONif and only if it lies within both parties' signeddeterminationBounds; otherwise the dispute endsUNRESOLVEDwithDETERMINATION_FAILED.
8. Execution Verification (MECH-2)
- Zero-Obligation Immediate
HONORED(MECH-2): An issue settled at the obligee's worst extreme (e.g.refundUsd = 0) creates no obligation. Ifobligorsis empty, the dispute settles immediately asHONORED. - Proof, Confirmation & Contest (
MECH-2): Obligors submitSUBMIT_EXECUTION_PROOF; obligees callCONFIRM_EXECUTIONorCONTEST_EXECUTION. AtexecutionDeadline, an obligor with uncontested proof is recorded asHONORED(preventing a silent obligee from manufacturing a breach), whereas missing or contested proof transitions toBREACH_REPORTED.
9. Cryptographic Verifiability (SEC3-4, SEC3-5, KEY-1, DISC-12)
- Transition-Signed Immutable Outcomes (
SEC3-4): Outcomes (SETTLED,SETTLEMENT_IMPROVED,HONORED,BREACH_REPORTED,UNRESOLVED, each carryingoutcomeHashin the audit chain,M7) are signed withEd25519Signature2026(agent-mediate/document/v2, bindingkeyIdandcreated; noexpiresAt, because outcomes are permanent records,D119) inside the state-transition database transaction and stored in the append-onlydispute_outcomestable.GET /v1/disputes/{id}/outcomeverifies the stored signature,auditRoot,termsHash, andoutcomeHashinside a snapshot-consistentREPEATABLE READtransaction and never signs on read. A snapshot whose signing key is later revoked is superseded by a re-signed snapshot at the same audit position (revision), never by editing the original. - Party Request Signature Proofs (
SEC3-5,SEC-1): Every party mutation's verified RFC 9421 Ed25519 proof (covering only the allowlisted components@method,@target-uri,content-digest, andidempotency-key, and bound to(disputeId, action, agentId),M1/M6) is stored in the append-onlydispute_signaturestable and served atGET /v1/disputes/{id}/signatures(full proofs for the caller's own actions and public-body counterparty actions;{ redacted: true, action: "confidential_action", agentId: null, proofHash }commitments for confidential-body counterparty actions). - Key History & Compromise Handling (
KEY-1):GET /.well-known/key-history.jsonpublishes the signedagent-mediate/key-history/v1chain (active,retired,revoked). Retired keys remain verifiable within[validFrom, validUntil]; revoked keys are rejected byverifyDocumentWithKeyHistory(clients pinned out of band to a compromisedplatformDidcheck that pin first and must re-pin to the rotated active key,M11). - Merkle Checkpoints & Base L2 Anchoring (
SEC3-5,DISC-12): Scheduled daily checkpoints (GET /v1/transparency/checkpoint,GET /v1/transparency/checkpoints/{seq}) publish signed binary SHA-256 Merkle roots using the RFC 6962 §2.1 largest-power-of-two split topology with string domain prefixes (agent-mediate/checkpoint-leaf/v1\n,agent-mediate/checkpoint-node/v1\n) over unique-disputeIdsnapshot tuples(disputeId, status, auditSeq, auditHead, outcomeHash)and deterministic 44-byte Base calldata (0x414d4350+ 8-bytecheckpointSeq+ 32-bytemerkleRoot).GET /v1/disputes/{id}/auditproves O(\log N) inclusion (expectedTotalLeaves === disputeCount) against the latest anchored checkpoint containing the dispute (falling back to the latest unanchored one); because leaves are per-checkpoint dispute snapshots rather than an append-only event log, cross-party split views are ruled out by comparing(checkpointSeq, merkleRoot, leafIndex)against Base L2 calldata (M3).