refactor: scope eval trust to reviewed runtime observations

.github/workflows/ci.yml

@@ -16,14 +16,14 @@ jobs:
 
       - name: Python checks
         run: |
-          python3 -m py_compile runner/cli.py container/invoke.py
+          python3 -m py_compile runner/cli.py container/invoke.py container/evidence_safety.py container/native_observer.py container/runtime_evidence.py tests/integration/run_code_mode_observer_probe.py tests/integration/run_runtime_evidence_acceptance.py
           python3 -m unittest discover -s tests -p 'test_*.py'
 
       - name: Build fake Copilot transport for action smoke test
         run: |
           cat > /tmp/Containerfile.fake-copilot <<'EOF'
           FROM alpine:3.22
-          ENTRYPOINT ["/bin/sh", "-c", "if [ -z \"$GITHUB_TOKEN\" ] || [ -n \"$COPILOT_GITHUB_TOKEN\" ] || [ -n \"$GH_TOKEN\" ] || [ \"$EVAL_REASONING\" != \"medium\" ]; then exit 42; fi; printf '%s\\n' '{\"schema\":\"opencode-eval-runner/v1\",\"transport\":\"github-copilot-cli\",\"model\":\"fake\",\"reasoning\":\"medium\",\"reasoning_source\":\"explicit\",\"agent\":\"eval-runner\",\"skill\":null,\"exit_code\":0,\"session_id\":null,\"text\":\"fake action smoke\",\"tools\":[],\"actions\":[],\"skills_loaded\":[],\"stderr\":\"\",\"stdout\":\"\"}'"]
+          ENTRYPOINT ["/bin/sh", "-c", "if [ -z \"$GITHUB_TOKEN\" ] || [ -n \"$COPILOT_GITHUB_TOKEN\" ] || [ -n \"$GH_TOKEN\" ] || [ \"$EVAL_REASONING\" != \"medium\" ]; then exit 42; fi; printf '%s\\n' '{\"schema\":\"opencode-eval-runner/v1\",\"transport\":\"github-copilot-cli\",\"model\":\"fake\",\"reasoning\":\"medium\",\"reasoning_source\":\"explicit\",\"agent\":\"eval-runner\",\"skill\":null,\"exit_code\":0,\"session_id\":null,\"text\":\"fake action smoke\",\"tools\":[],\"actions\":[],\"skills_loaded\":[],\"stderr\":\"\",\"stdout\":\"\",\"runtime_evidence\":{\"schema\":\"opencode-eval-runner/runtime-evidence/v1\",\"status\":\"unsupported\",\"evidence_eligible\":false,\"observations\":[],\"coverage\":{\"observation_closed\":{\"state\":\"unsupported\",\"reason\":\"observer_not_implemented\"},\"process_state\":\"unsupported\",\"starts\":{\"state\":\"unsupported\",\"reason\":\"observer_not_implemented\"},\"terminals\":{\"state\":\"unsupported\",\"reason\":\"observer_not_implemented\"},\"missing_terminals\":{\"state\":\"unsupported\",\"reason\":\"observer_not_implemented\"},\"observer_failures\":{\"state\":\"unsupported\",\"reason\":\"observer_not_implemented\"},\"callback_failures\":{\"state\":\"unsupported\",\"reason\":\"observer_not_implemented\"},\"losses\":[],\"unsupported\":[\"observer_not_implemented\"],\"boundaries\":{\"native\":{\"status\":\"unsupported\",\"evidence_eligible\":false,\"starts\":{\"state\":\"unsupported\",\"reason\":\"observer_not_implemented\"},\"terminals\":{\"state\":\"unsupported\",\"reason\":\"observer_not_implemented\"},\"missing_terminals\":{\"state\":\"unsupported\",\"reason\":\"observer_not_implemented\"},\"issues\":[\"observer_not_implemented\"]},\"code_mode_execution\":{\"status\":\"unsupported\",\"evidence_eligible\":false,\"starts\":{\"state\":\"unsupported\",\"reason\":\"observer_not_implemented\"},\"terminals\":{\"state\":\"unsupported\",\"reason\":\"observer_not_implemented\"},\"missing_terminals\":{\"state\":\"unsupported\",\"reason\":\"observer_not_implemented\"},\"issues\":[\"observer_not_implemented\"]},\"code_mode_finality\":{\"status\":\"unsupported\",\"evidence_eligible\":false,\"starts\":{\"state\":\"unsupported\",\"reason\":\"observer_not_implemented\"},\"terminals\":{\"state\":\"unsupported\",\"reason\":\"observer_not_implemented\"},\"missing_terminals\":{\"state\":\"unsupported\",\"reason\":\"observer_not_implemented\"},\"issues\":[\"observer_not_implemented\"]}}}}}'"]
           EOF
           docker build -f /tmp/Containerfile.fake-copilot -t opencode-eval-runner:fake-copilot /tmp
           printf '%s\n' 'action smoke prompt' > /tmp/action-smoke-prompt.txt
@@ -64,11 +64,19 @@ jobs:
           assert result["reasoning"] == "medium"
           assert result["reasoning_source"] == "explicit"
           assert result["text"] == "fake action smoke"
+          assert result["runtime_evidence"]["status"] == "unsupported"
+          assert result["runtime_evidence"]["evidence_eligible"] is False
           PY
 
       - name: Build OpenCode transport image
         run: docker build -f Containerfile --target opencode -t opencode-eval-runner:opencode-test .
 
+      - name: Probe stock Code Mode inner observation boundary
+        run: |
+          python3 tests/integration/run_code_mode_observer_probe.py \
+            --image opencode-eval-runner:opencode-test \
+            --output /tmp/code-mode-observer-probe
+
       - name: Build Copilot transport image
         run: docker build -f Containerfile --target copilot -t opencode-eval-runner:copilot-test .
 

.github/workflows/native-observer-integration.yml

@@ -0,0 +1,53 @@
+name: Stock native observer integration
+
+on:
+  pull_request:
+    paths:
+      - 'container/invoke.py'
+      - 'container/native_observer.py'
+      - 'container/native_observer.ts'
+      - 'tests/integration/native_observer_probe.ts'
+      - 'tests/integration/run_native_observer_probe.py'
+      - 'tests/test_native_observer.py'
+      - '.github/workflows/native-observer-integration.yml'
+
+permissions:
+  contents: read
+
+jobs:
+  stock-native-observer:
+    runs-on: ubuntu-latest
+    timeout-minutes: 10
+    steps:
+      - uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262
+        with:
+          ref: ${{ github.event.pull_request.head.sha }}
+          persist-credentials: false
+
+      - name: Verify probe syntax
+        run: python3 -m py_compile container/native_observer.py tests/integration/run_native_observer_probe.py
+
+      - name: Build runner with stock OpenCode 2.0.23
+        run: docker build -f Containerfile --target opencode -t opencode-eval-runner:native-observer-probe .
+
+      - name: Run provider-free native observer probe
+        run: |
+          docker run --rm \
+            --network none \
+            --tmpfs /tmp:rw,exec,nosuid,nodev,size=1g,mode=1777 \
+            --tmpfs /workspace:rw,nosuid,nodev,size=64m,mode=1777 \
+            --volume "$PWD:/probe-repo:ro" \
+            --entrypoint python3 \
+            opencode-eval-runner:native-observer-probe \
+            /probe-repo/tests/integration/run_native_observer_probe.py \
+            > native-observer-probe.json
+          cat native-observer-probe.json
+
+      - name: Preserve probe report
+        if: always()
+        uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02
+        with:
+          name: native-observer-${{ github.event.pull_request.head.sha }}
+          path: native-observer-probe.json
+          if-no-files-found: warn
+          retention-days: 14

.github/workflows/runtime-evidence-acceptance.yml

@@ -0,0 +1,47 @@
+name: Provider-free runtime evidence acceptance
+
+on:
+  pull_request:
+    paths:
+      - 'Containerfile'
+      - 'container/**'
+      - 'runner/**'
+      - 'tests/integration/**'
+      - 'tests/test_runtime_evidence_acceptance.py'
+      - '.github/workflows/runtime-evidence-acceptance.yml'
+  workflow_dispatch:
+
+permissions:
+  contents: read
+
+jobs:
+  provider-free-acceptance:
+    runs-on: ubuntu-latest
+    timeout-minutes: 15
+    steps:
+      - uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262
+        with:
+          persist-credentials: false
+
+      - name: Check acceptance driver
+        run: |
+          python3 -m py_compile tests/integration/run_runtime_evidence_acceptance.py
+          python3 -m unittest discover -s tests -p 'test_runtime_evidence_acceptance.py' -v
+
+      - name: Build stock OpenCode 2.0.23 runner image
+        run: docker build -f Containerfile --target opencode -t opencode-eval-runner:runtime-evidence-acceptance .
+
+      - name: Run provider-free acceptance gate
+        run: |
+          python3 tests/integration/run_runtime_evidence_acceptance.py \
+            --image opencode-eval-runner:runtime-evidence-acceptance \
+            --output runtime-evidence-acceptance
+
+      - name: Preserve sanitized acceptance report
+        if: always()
+        uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02
+        with:
+          name: runtime-evidence-acceptance-${{ github.event.pull_request.head.sha || github.sha }}
+          path: runtime-evidence-acceptance/
+          if-no-files-found: error
+          retention-days: 14

Containerfile

@@ -1,5 +1,5 @@
 FROM node:24-bookworm-slim@sha256:0e0ff40c39bc087845bfb27465a0df4ea419520094bc35842ff83dd8cbe6f9b6 AS opencode-builder
-ARG OPENCODE_VERSION=2.0.18
+ARG OPENCODE_VERSION=2.0.23
 RUN npm install --global "@opencode/cli@${OPENCODE_VERSION}" \
     && resolved="$(readlink -f "$(command -v opencode)")" \
     && test -x "$resolved" \