Run cf-integration 0.5.0 conformance on every PR

.github/workflows/ci.yml

@@ -77,7 +77,7 @@ jobs:
     steps:
       - uses: actions/checkout@v6.0.2
         with:
-          # Match the PR revision selected by /conformance.
+          # Match the PR head revision used by the conformance workflow.
           ref: ${{ github.event.pull_request.head.sha || github.sha }}
       - uses: dtolnay/rust-toolchain@stable
       - uses: Swatinem/rust-cache@v2.9.1

.github/workflows/conformance.yml

@@ -1,68 +1,37 @@
 name: Conformance
-run-name: "Conformance for PR #${{ github.event.issue.number }}"
+run-name: "Conformance for PR #${{ github.event.pull_request.number }}"
 
 on:
-  issue_comment:
-    types: [created]
+  pull_request:
 
 env:
   CARGO_TERM_COLOR: always
 
 jobs:
   conformance:
     name: conformance
-    if: >-
-      github.event.issue.pull_request &&
-      github.event.comment.body == '/conformance' &&
-      contains(fromJSON('["OWNER","MEMBER","COLLABORATOR"]'), github.event.comment.author_association)
     concurrency:
-      group: conformance-pr-${{ github.event.issue.number }}
+      group: conformance-pr-${{ github.event.pull_request.number }}
       cancel-in-progress: true
     permissions:
       actions: read
       contents: read
-      pull-requests: read
-      statuses: write
     runs-on: ubuntu-latest
     timeout-minutes: 60
     steps:
-      - name: Resolve the exact PR revision
-        id: revision
-        env:
-          GH_TOKEN: ${{ github.token }}
-          PR_NUMBER: ${{ github.event.issue.number }}
-          REPOSITORY: ${{ github.repository }}
-        run: >-
-          gh api "repos/$REPOSITORY/pulls/$PR_NUMBER"
-          --jq '"head_sha=\(.head.sha)"'
-          >> "$GITHUB_OUTPUT"
-
-      - name: Publish the pending PR status
-        env:
-          GH_TOKEN: ${{ github.token }}
-          HEAD_SHA: ${{ steps.revision.outputs.head_sha }}
-          REPOSITORY: ${{ github.repository }}
-          RUN_URL: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}
-        run: >-
-          gh api --method POST "repos/$REPOSITORY/statuses/$HEAD_SHA"
-          -f state=pending
-          -f context=conformance
-          -f description='Conformance is running'
-          -f target_url="$RUN_URL"
-
       - name: Check out data plane
         uses: actions/checkout@v6.0.2
         with:
           fetch-depth: 0
           persist-credentials: false
-          ref: ${{ steps.revision.outputs.head_sha }}
+          ref: ${{ github.event.pull_request.head.sha }}
 
       - uses: taiki-e/install-action@v2.75.27
         with:
           tool: cargo-binstall
 
-      - name: Install cf-integration 0.3.2 binary
-        run: cargo binstall cf-integration@0.3.2 --no-confirm
+      - name: Install cf-integration 0.5.0 binary
+        run: cargo binstall cf-integration@0.5.0 --no-confirm
 
       - name: Prepare the exact data-plane image
         env:
@@ -74,25 +43,8 @@ jobs:
           --image contextforge-data-plane:conformance
 
       - name: Run strict modern conformance
-        id: conformance
         env:
           CF_DATAPLANE_IMAGE: contextforge-data-plane:conformance
           CF_DATAPLANE_PULL_POLICY: never
           CF_DATAPLANE_REF: ""
         run: make conformance
-
-      - name: Publish the final PR status
-        if: always() && steps.revision.outputs.head_sha != ''
-        env:
-          DESCRIPTION: Conformance ${{ job.status }}
-          GH_TOKEN: ${{ github.token }}
-          HEAD_SHA: ${{ steps.revision.outputs.head_sha }}
-          REPOSITORY: ${{ github.repository }}
-          RUN_URL: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}
-          STATE: ${{ job.status == 'success' && 'success' || job.status == 'failure' && 'failure' || 'error' }}
-        run: >-
-          gh api --method POST "repos/$REPOSITORY/statuses/$HEAD_SHA"
-          -f state="$STATE"
-          -f context=conformance
-          -f description="$DESCRIPTION"
-          -f target_url="$RUN_URL"

_context/wiki/getting-started.md

@@ -270,7 +270,7 @@ Install the same released harness version used by CI. Conformance and Inspector
 install and run Node/npm only inside Docker images.
 
 ```bash
-cargo binstall cf-integration@0.3.2 --no-confirm
+cargo binstall cf-integration@0.5.0 --no-confirm
 make conformance
 ```
 

_context/wiki/performance.md

@@ -1,7 +1,7 @@
 # Performance and Load Testing
 
 Load testing is owned by [`cf-integration`](https://crates.io/crates/cf-integration).
-The commands below match **0.3.2**, the version pinned by this repository's
+The commands below match **0.5.0**, the version pinned by this repository's
 conformance workflow. The old `scripts/cf-integration.sh` wrapper is no longer
 in this repository.
 
@@ -11,8 +11,8 @@ Use Docker with enough resources for the selected topology. Install the pinned
 CLI and check its command reference:
 
 ```bash
-cargo binstall cf-integration@0.3.2 --no-confirm
-cf-integration load --help
+cargo binstall cf-integration@0.5.0 --no-confirm
+cf-integration load run --help
 ```
 
 The standalone lane starts the external dataplane, Redis, nginx, and a fixture
@@ -22,7 +22,7 @@ does not depend on the unsupported external `tools/list` method:
 ```bash
 CF_INTEGRATION_DIR="$PWD/.integration" \
 CF_DATAPLANE_REPO="$PWD" CF_DATAPLANE_REF="$(git rev-parse HEAD)" \
-  cf-integration load --lane external --protocol-version modern --standalone \
+  cf-integration load run --lane external --client-era modern --standalone \
   --users 1 --spawn-rate 1 --run-time 10s
 ```
 
@@ -34,7 +34,7 @@ comparing them. All external examples target modern MCP `2026-07-28`.
 ```bash
 CF_INTEGRATION_DIR="$PWD/.integration" \
 CF_DATAPLANE_REPO="$PWD" CF_DATAPLANE_REF="$(git rev-parse HEAD)" \
-  cf-integration load --lane external --protocol-version modern --standalone \
+  cf-integration load run --lane external --client-era modern --standalone \
   --users 20 --spawn-rate 5 --run-time 2m
 ```
 
@@ -60,17 +60,17 @@ versions alongside the report.
 Omit `--standalone` to include the control plane and its publication path:
 
 ```bash
-cf-integration load --lane external --protocol-version modern \
+cf-integration load run --lane external --client-era modern \
   --users 20 --spawn-rate 5 --run-time 2m
-cf-integration load --lane builtin --protocol-version modern \
+cf-integration load run --lane builtin --client-era modern \
   --users 20 --spawn-rate 5 --run-time 2m
 ```
 
 Use equivalent backends, tools, hardware, authentication, policy, cache settings,
 and client metadata for comparisons. A full-stack failure while discovering or
 publishing the catalog is a setup failure, not a throughput measurement.
 Standalone measurements omit control-plane publication and must be labeled as
-such. See the [pinned harness documentation](https://github.com/contextforge-org/contextforge-dev-tools/blob/v0.3.2/README.md)
+such. See the [pinned harness documentation](https://github.com/contextforge-org/contextforge-dev-tools/blob/v0.5.0/README.md)
 for topology and source selection.
 
 ## Benchmark Controls

_context/wiki/testing.md

@@ -88,15 +88,13 @@ owns the official fixture, control-plane registration, Compose topology, server
 and client runners, result rendering, and transactional baseline handling. This
 repository keeps only the CI invocation, Make targets, and expected findings.
 
-Comment exactly `/conformance` on a pull request to run the **Conformance**
-Actions workflow. Only repository owners, members, and collaborators can start
-it. The workflow sets a pending `conformance` commit status, tests the pull request
-head commit, and updates that status with the result. The `issue_comment`
-workflow itself is read from the default branch, so a PR edit to that workflow
-does not change the command handling until merged. CI builds and names the
-conformance binary artifact using that same head SHA and retains it for 90 days,
-so changes to `main` do not invalidate the artifact. It runs the modern client
-and modern server eras through the external dataplane in standalone mode. This
+The **Conformance** Actions workflow runs automatically for every pull request
+revision and reports its result as a native pull request check. It checks out
+the pull request head commit while CI builds and names the conformance binary
+artifact using that same head SHA. The harness waits for that artifact when the
+workflows start concurrently, and CI retains it for 90 days, so changes to
+`main` do not invalidate the artifact. Conformance runs the modern client and
+modern server eras through the external dataplane in standalone mode. This
 starts Redis, the dataplane, nginx, and the official fixture without the control
 plane. The harness discovers the fixture's tools, resources, templates, and
 prompts and publishes their routes and actual tool schemas directly to Redis

tests/conformance/baselines/2026-07-28/modern/external-data-plane.yml

@@ -127,6 +127,10 @@ findings:
   check: sep-2575-server-declares-prompts-in-discover
   name: ServerDeclaresPromptsInDiscover
   status: FAILURE
+- scenario: tools-call-with-progress
+  check: tools-call-with-progress
+  name: ToolsCallWithProgress
+  status: FAILURE
 - scenario: tools-list
   check: tools-list
   name: ToolsList