Merge remote-tracking branch 'origin/main' into pr-2816

Author: Kludex

.github/actions/conformance/client.py

@@ -6,6 +6,9 @@
 Contract:
     - MCP_CONFORMANCE_SCENARIO env var -> scenario name
     - MCP_CONFORMANCE_CONTEXT env var -> optional JSON (for client-credentials scenarios)
+    - MCP_CONFORMANCE_PROTOCOL_VERSION env var -> spec version the harness mock
+      server is speaking (e.g. "2025-11-25", "2026-07-28"). Always set; defaults
+      to the harness's LATEST_SPEC_VERSION when --spec-version is omitted.
     - Server URL as last CLI argument (sys.argv[1])
     - Must exit 0 within 30 seconds
 
@@ -50,6 +53,13 @@
 )
 logger = logging.getLogger(__name__)
 
+#: Spec version the harness is running this scenario at (e.g. "2025-11-25",
+#: "2026-07-28"). The harness always sets this (it falls back to its own
+#: LATEST_SPEC_VERSION when --spec-version is omitted), so None means we were
+#: invoked outside the harness. Handlers that need to take the stateless 2026
+#: path will branch on this once the SDK has one; today it is logged only.
+PROTOCOL_VERSION: str | None = os.environ.get("MCP_CONFORMANCE_PROTOCOL_VERSION")
+
 # Type for async scenario handler functions
 ScenarioHandler = Callable[[str], Coroutine[Any, None, None]]
 
@@ -347,6 +357,7 @@ def main() -> None:
 
     server_url = sys.argv[1]
     scenario = os.environ.get("MCP_CONFORMANCE_SCENARIO")
+    logger.debug(f"Conformance protocol version: {PROTOCOL_VERSION!r}")
 
     if scenario:
         logger.debug(f"Running explicit scenario '{scenario}' against {server_url}")

.github/actions/conformance/expected-failures.2026-07-28.yml

@@ -0,0 +1,123 @@
+# Expected failures for the carried-forward 2026-07-28 legs
+# (`--suite all --spec-version 2026-07-28` for both server and client).
+#
+# This baseline is separate from expected-failures.yml because entries are
+# keyed by scenario name only: a scenario that passes at its default version
+# in the 2025 legs but fails when forced to 2026-07-28 (or vice versa) cannot
+# be expressed in a shared file (the passing leg would flag the entry as
+# stale). Like expected-failures.yml, this single file covers both
+# directions: the client 2026 leg reads the `client:` section and the server
+# 2026 leg reads the `server:` section. Both burn down independently of the
+# 2025 legs.
+#
+# Baseline established against @modelcontextprotocol/conformance pinned in
+# .github/workflows/conformance.yml (CONFORMANCE_VERSION = 0.2.0-alpha.4).
+# New conformance releases are adopted by deliberately bumping that pin and
+# reconciling both this file and expected-failures.yml in the same change.
+#
+# Entries are grouped by what unblocks them. As each gap closes 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:
+  # --- No stateless client path on main yet ---
+  # client.py drives the 2025 stateful lifecycle (initialize handshake +
+  # session). The 2026-mode mock server is stateless, so the call sequence
+  # never reaches the assertion. Unblocks when client.py's is_modern_protocol()
+  # branch takes the per-request _meta path.
+  - tools_call
+
+  # --- SEP-837 (application_type during DCR) ---
+  # The sep-837-application-type-present check only fires on 2026-version
+  # runs; the client omits application_type during Dynamic Client
+  # Registration, so every auth scenario that reaches DCR fails it on this
+  # leg (the same scenarios pass at their default version in the 2025 legs).
+  - auth/metadata-default
+  - auth/metadata-var1
+  - auth/metadata-var2
+  - auth/metadata-var3
+  - auth/scope-from-www-authenticate
+  - auth/scope-from-scopes-supported
+  - auth/scope-omitted-when-undefined
+  - auth/token-endpoint-auth-basic
+  - auth/token-endpoint-auth-post
+  - auth/token-endpoint-auth-none
+  - auth/offline-access-not-supported
+
+  # --- Auth scenarios cut short by the 2026 connection lifecycle ---
+  # The auth fixture flow drives the 2025 stateful lifecycle; the 2026-mode
+  # mock rejects the MCP POST before the scope-escalation behaviour these
+  # scenarios measure, so no authorization requests are observed. Unblocks
+  # when client.py's auth flow speaks the 2026 per-request lifecycle.
+  - auth/scope-step-up
+  - auth/scope-retry-limit
+
+  # --- Same gaps as the 2025 baseline (fail identically when forced to 2026-07-28) ---
+  # SEP-2575 (request metadata / _meta envelope): client does not populate the
+  # _meta envelope or the MCP-Protocol-Version header semantics yet.
+  - request-metadata
+  # SEP-2322 (multi-round-trip requests): client does not echo requestState /
+  # handle IncompleteResult yet.
+  - sep-2322-client-request-state
+  # SEP-2243 (HTTP standardization): no fixture handler / client header support yet.
+  - http-custom-headers
+  - http-invalid-tool-headers
+  # SEP-2106 (JSON Schema $ref handling): client still dereferences network $refs.
+  - json-schema-ref-no-deref
+  # SEP-2468 (authorization response iss parameter): not implemented in the client.
+  - auth/iss-supported
+  - auth/iss-not-advertised
+  - auth/iss-supported-missing
+  - auth/iss-wrong-issuer
+  - auth/iss-unexpected
+  - auth/iss-normalized
+  - auth/metadata-issuer-mismatch
+  # SEP-2352 (authorization server migration): client does not re-register when
+  # PRM authorization_servers changes.
+  - auth/authorization-server-migration
+  # auth/enterprise-managed-authorization (SEP-990) is in the 2025 baseline but
+  # NOT here: the harness skips it as inapplicable at --spec-version 2026-07-28
+  # (it is an extension scenario not carried into the 2026 wire), so it is
+  # neither run nor evaluated on this leg.
+
+server:
+  # --- Carried-forward 2025-era scenarios still failing on the 2026 wire ---
+  # The stateless 2026 path now reaches handlers for plain request/response
+  # scenarios; tools-call-with-progress still fails because the stateless
+  # server has no channel for server→client progress notifications.
+  - tools-call-with-progress
+  # SEP-2106 (JSON Schema 2020-12 in tool inputSchema): the fixture tool's
+  # schema has none of the 2020-12 keywords the scenario checks. The scenario
+  # is in `--suite all` but not `--suite active`, so this is the only leg that
+  # runs it; it fails identically at 2025-11-25 (not a 2026-path regression).
+  - json-schema-2020-12
+
+  # --- Draft scenarios (same failures and reasons as the `--suite draft` leg) ---
+  # SEP-2575 (stateless HTTP / _meta envelope): server has no stateless mode,
+  # _meta-derived capabilities, error-code mappings, or server/discover yet.
+  - server-stateless
+  # SEP-2322 (multi-round-trip requests / IncompleteResult): not implemented.
+  - input-required-result-basic-elicitation
+  - input-required-result-basic-sampling
+  - input-required-result-basic-list-roots
+  - input-required-result-request-state
+  - input-required-result-multiple-input-requests
+  - input-required-result-multi-round
+  - input-required-result-non-tool-request
+  - input-required-result-result-type
+  - input-required-result-tampered-state
+  - input-required-result-capability-check
+  - input-required-result-validate-input
+  # SEP-2243 (HTTP header standardization): -32020 HeaderMismatch handling and
+  # case-insensitive/whitespace-trimmed header validation not implemented.
+  - http-header-validation
+
+  # --- WARNING-only entries ---
+  # These scenarios emit no FAILURE checks, only SHOULD-level WARNINGs, but
+  # the expected-failures evaluator counts WARNINGs as failures. Same entries
+  # as the draft suite in expected-failures.yml.
+  # SEP-2164: server returns -32600 (not -32602) and omits error.data.uri.
+  - sep-2164-resource-not-found
+  # SEP-2322 SHOULD-level behaviour (re-request missing inputResponses).
+  - input-required-result-missing-input-response

.github/actions/conformance/expected-failures.yml

@@ -0,0 +1,83 @@
+# 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 @modelcontextprotocol/conformance pinned in
+# .github/workflows/conformance.yml (CONFORMANCE_VERSION = 0.2.0-alpha.4).
+# 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:
+  # --- Draft-spec scenarios (in `--suite draft`, also part of `--suite all`) ---
+  # SEP-2575 (request metadata / _meta envelope): client does not populate the
+  # _meta envelope or the MCP-Protocol-Version header semantics yet.
+  - request-metadata
+  # SEP-2322 (multi-round-trip requests): client does not echo requestState /
+  # handle IncompleteResult yet.
+  - sep-2322-client-request-state
+  # SEP-2243 (HTTP standardization): no fixture handler / client header support yet.
+  - http-custom-headers
+  - http-invalid-tool-headers
+  # SEP-2106 (JSON Schema $ref handling): client still dereferences network $refs.
+  - json-schema-ref-no-deref
+  # SEP-2468 (authorization response iss parameter): not implemented in the client.
+  - auth/iss-supported
+  - auth/iss-not-advertised
+  - auth/iss-supported-missing
+  - auth/iss-wrong-issuer
+  - auth/iss-unexpected
+  - auth/iss-normalized
+  - auth/metadata-issuer-mismatch
+  # SEP-2352 (authorization server migration): client does not re-register when
+  # PRM authorization_servers changes.
+  - auth/authorization-server-migration
+  # SEP-837 (application_type during DCR): the check only fires on draft-version
+  # runs; this draft scenario is the one place the client still hits it.
+  - auth/offline-access-not-supported
+
+  # --- Pre-existing scenarios that fail on checks added after conformance 0.1.15 ---
+  # SEP-2350 (scope step-up): WARNING-only; the expected-failures evaluator
+  # counts WARNINGs as failures.
+  - auth/scope-step-up
+  # SEP-990 (enterprise-managed authorization extension): no fixture handler /
+  # client support for the token-exchange + JWT bearer flow.
+  - auth/enterprise-managed-authorization
+
+server:
+  # --- Draft-spec scenarios (in `--suite draft`; the `active` suite is green) ---
+  # SEP-2575 (stateless HTTP / _meta envelope): server has no stateless mode,
+  # _meta-derived capabilities, error-code mappings, or server/discover yet.
+  - server-stateless
+  # SEP-2322 (multi-round-trip requests / IncompleteResult): not implemented;
+  # most scenarios currently fail early with "Missing session ID" because
+  # mcp-everything-server only runs in stateful mode.
+  - input-required-result-basic-elicitation
+  - input-required-result-basic-sampling
+  - input-required-result-basic-list-roots
+  - input-required-result-request-state
+  - input-required-result-multiple-input-requests
+  - input-required-result-multi-round
+  - input-required-result-non-tool-request
+  - input-required-result-result-type
+  - input-required-result-tampered-state
+  - input-required-result-capability-check
+  # SEP-2243 (HTTP header standardization): -32020 HeaderMismatch handling and
+  # case-insensitive/whitespace-trimmed header validation not implemented.
+  - http-header-validation
+  # WARNING-only entries: these scenarios emit no FAILURE checks, only SHOULD-level
+  # WARNINGs, but the expected-failures evaluator counts WARNINGs as failures.
+  # SEP-2164: server returns -32600 (not -32602) and omits error.data.uri.
+  - sep-2164-resource-not-found
+  # SEP-2322 SHOULD-level behaviour (re-request missing inputResponses).
+  - input-required-result-missing-input-response
+  # SEP-2322 negative-case scenarios: input-required-result-validate-input is
+  # now baselined (added when the stateless path landed — the stateless server
+  # reaches the handler, so the previous accidental pass via -32600 "Missing
+  # session ID" no longer applies). input-required-result-unsupported-methods
+  # is intentionally NOT baselined: it still passes for now; add it once it
+  # starts failing for real.
+  - input-required-result-validate-input

.github/actions/conformance/run-server.sh

@@ -7,15 +7,36 @@ SERVER_URL="http://localhost:${PORT}/mcp"
 SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
 cd "$SCRIPT_DIR/../../.."
 
-# Start everything-server
+# Refuse to start if something is already listening on the port. The readiness
+# check below cannot tell our server apart from a stale one, so a leftover
+# listener would mean silently running conformance against old code.
+if (: > "/dev/tcp/localhost/${PORT}") 2>/dev/null; then
+    echo "Error: port ${PORT} is already in use." >&2
+    echo "Stop the stale process first (lsof -ti:${PORT} -sTCP:LISTEN | xargs kill) or set PORT to a free port." >&2
+    exit 1
+fi
+
+echo "Starting mcp-everything-server on port ${PORT}..."
 uv run --frozen mcp-everything-server --port "$PORT" &
 SERVER_PID=$!
-trap "kill $SERVER_PID 2>/dev/null || true; wait $SERVER_PID 2>/dev/null || true" EXIT
 
-# Wait for server to be ready
+cleanup() {
+    echo "Stopping server (PID: ${SERVER_PID})..."
+    kill $SERVER_PID 2>/dev/null || true
+    wait $SERVER_PID 2>/dev/null || true
+}
+trap cleanup EXIT
+
+# Wait for server to be ready. --max-time keeps a hung listener from wedging
+# the loop, and a dead server process fails fast instead of retrying.
+echo "Waiting for server to be ready..."
 MAX_RETRIES=30
 RETRY_COUNT=0
-while ! curl -s "$SERVER_URL" > /dev/null 2>&1; do
+while ! curl -s --max-time 2 "$SERVER_URL" > /dev/null 2>&1; do
+    if ! kill -0 $SERVER_PID 2>/dev/null; then
+        echo "Server process exited unexpectedly" >&2
+        exit 1
+    fi
     RETRY_COUNT=$((RETRY_COUNT + 1))
     if [ $RETRY_COUNT -ge $MAX_RETRIES ]; then
         echo "Server failed to start after ${MAX_RETRIES} retries" >&2
@@ -26,5 +47,5 @@ done
 
 echo "Server ready at $SERVER_URL"
 
-# Run conformance tests
-npx @modelcontextprotocol/conformance@0.1.10 server --url "$SERVER_URL" "$@"
+npx --yes @modelcontextprotocol/conformance@"${CONFORMANCE_VERSION:?set CONFORMANCE_VERSION (pinned in .github/workflows/conformance.yml)}" \
+    server --url "$SERVER_URL" "$@"

.github/dependabot.yml

@@ -1,9 +1,21 @@
 version: 2
 updates:
+  - package-ecosystem: "uv"
+    directory: "/"
+    schedule:
+      interval: monthly
+    cooldown:
+      default-days: 14
+    groups:
+      python-packages:
+        patterns:
+          - "*"
   - package-ecosystem: "github-actions"
     directory: "/"
     schedule:
       interval: monthly
+    cooldown:
+      default-days: 14
     groups:
       github-actions:
         patterns:

.github/workflows/claude.yml

@@ -27,14 +27,14 @@ jobs:
       actions: read # Required for Claude to read CI results on PRs
     steps:
       - name: Checkout repository
-        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+        uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10 # v6.0.3
         with:
           fetch-depth: 1
           persist-credentials: false
 
       - name: Run Claude Code
         id: claude
-        uses: anthropics/claude-code-action@2f8ba26a219c06cfb0f468eef8d97055fa814f97 # v1.0.53
+        uses: anthropics/claude-code-action@d5726de019ec4498aa667642bc3a80fca83aa102 # v1.0.148
         with:
           anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }} # zizmor: ignore[secrets-outside-env]
           use_commit_signing: true