expected-failures.yml

# Conformance scenarios not yet passing against the Python SDK on main.
# CI exits 0 if only these fail, exits 1 on unexpected failures or stale entries.
#
# Baseline established against the harness pinned via CONFORMANCE_PKG in
# .github/workflows/conformance.yml. New conformance releases are adopted by
# deliberately bumping that pin and reconciling both this file and
# expected-failures.2026-07-28.yml in the same change.
#
# Entries are grouped by SEP. As each SEP lands in the SDK the corresponding
# scenarios start passing and MUST be removed from this list (the runner fails
# on stale entries), so the baseline burns down per milestone.

client:
  # SEP-1932 (DPoP): the SDK's OAuth client does not implement DPoP proofs.
  # These scenarios are new in the da56f663 referee pin. The entries are
  # per-check (conformance #406) because both scenarios pass their
  # non-DPoP checks (discovery, token acquisition, request flow) live.
  - auth/dpop:sep-1932-client-token-request-proof
  - auth/dpop:sep-1932-client-dpop-auth-scheme
  - auth/dpop:sep-1932-client-fresh-proof
  - auth/dpop-nonce:sep-1932-client-token-request-proof
  - auth/dpop-nonce:sep-1932-client-dpop-auth-scheme
  - auth/dpop-nonce:sep-1932-client-fresh-proof
  - auth/dpop-nonce:sep-1932-client-as-nonce
  - auth/dpop-nonce:sep-1932-client-rs-nonce
  # Workload identity federation: the OAuth client does not implement the
  # urn:ietf:params:oauth:grant-type:jwt-bearer grant (it answers with
  # authorization_code). Also new in the da56f663 referee pin; per-check for
  # the same reason.
  - auth/wif-jwt-bearer:wif-grant-type

server:
  # SEP-2663 (io.modelcontextprotocol/tasks): the SDK does not implement the
  # tasks extension yet. These extension-tagged scenarios are selected only by
  # the bare `--suite all` leg — extension scenarios never match a
  # --spec-version filter and the active/draft suites exclude them — so these
  # entries are inert for the other legs that read this file.
  #
  # `tasks-status-notifications` is intentionally NOT listed: the harness
  # skips it unconditionally (pending its rewrite against subscriptions/
  # listen), and a baseline entry for a scenario with no failing checks is
  # flagged stale.
  - tasks-lifecycle
  - tasks-capability-negotiation
  - tasks-wire-fields
  - tasks-request-state-removal
  - tasks-mrtr-input
  - tasks-request-headers
  - tasks-dispatch-and-envelope
  - tasks-required-task-error
  - tasks-mrtr-composition