feat: merge module map, bounded agent context, durable evidence, and review UX into main

.github/workflows/benchmark.yml

@@ -112,6 +112,8 @@ jobs:
         env:
           RUNS: ${{ matrix.runs }}
           WARMUPS: ${{ matrix.warmups }}
+          SCENARIO_PROFILE: ${{ matrix.profile }}
+          STARTUP_RUNS: "3"
           CPUS: ${{ matrix.cpus }}
           MEMORY: ${{ matrix.memory }}
         run: |
@@ -125,6 +127,8 @@ jobs:
             --target . \
             --runs "${{ matrix.runs }}" \
             --warmups "${{ matrix.warmups }}" \
+            --scenario-profile "${{ matrix.profile }}" \
+            --startup-runs 3 \
             --tmp-dir "/tmp/codeclone-bench-${{ matrix.label }}" \
             --output "$BENCH_JSON"
 
@@ -143,21 +147,39 @@ jobs:
               raise SystemExit(1)
 
           payload = json.loads(report_path.read_text(encoding="utf-8"))
+          startup_probes = payload.get("startup_probes", [])
           scenarios = payload.get("scenarios", [])
           comparisons = payload.get("comparisons", {})
 
           print("CodeClone benchmark summary")
           print(f"label={os.environ.get('RUNNER_OS','unknown').lower()} / {os.environ.get('GITHUB_JOB','benchmark')}")
+          if startup_probes:
+              print("startup probes:")
+              for probe in startup_probes:
+                  name = str(probe.get("name", "unknown"))
+                  stats = probe.get("stats_seconds", {})
+                  cpu_stats = probe.get("child_cpu_stats_seconds", {})
+                  print(
+                      f"- {name:22s} median={float(stats.get('median', 0.0)):.4f}s "
+                      f"first={float(probe.get('first_seconds', 0.0)):.4f}s "
+                      f"cpu={float(cpu_stats.get('median', 0.0)):.4f}s"
+                  )
           for scenario in scenarios:
               name = str(scenario.get("name", "unknown"))
               stats = scenario.get("stats_seconds", {})
+              cpu_stats = scenario.get("child_cpu_stats_seconds", {})
+              inventory = scenario.get("inventory_sample", {})
               median = float(stats.get("median", 0.0))
               p95 = float(stats.get("p95", 0.0))
               stdev = float(stats.get("stdev", 0.0))
               digest = str(scenario.get("digest", ""))
               print(
                   f"- {name:16s} median={median:.4f}s "
-                  f"p95={p95:.4f}s stdev={stdev:.4f}s digest={digest}"
+                  f"p95={p95:.4f}s stdev={stdev:.4f}s "
+                  f"cpu={float(cpu_stats.get('median', 0.0)):.4f}s "
+                  f"files={inventory.get('analyzed', 0)}/{inventory.get('cached', 0)} "
+                  f"artifacts={float(scenario.get('artifact_total_kib_sample', 0.0)):.1f}KiB "
+                  f"exit={scenario.get('exit_code_counts', {})} digest={digest}"
               )
 
           if comparisons:
@@ -174,24 +196,57 @@ jobs:
               "",
               f"- Tool: `{payload['tool']['name']} {payload['tool']['version']}`",
               f"- Target: `{payload['config']['target']}`",
+              f"- Scenario profile: `{payload['config'].get('scenario_profile', 'smoke')}`",
               f"- Runs: `{payload['config']['runs']}`",
               f"- Warmups: `{payload['config']['warmups']}`",
+              f"- Startup runs: `{payload['config'].get('startup_runs', 0)}`",
               f"- Generated: `{payload['generated_at_utc']}`",
               "",
-              "### Scenarios",
-              "",
-              "| Scenario | Median (s) | p95 (s) | Stdev (s) | Deterministic | Digest |",
-              "|---|---:|---:|---:|:---:|---|",
           ]
 
+          if startup_probes:
+              lines.extend(
+                  [
+                      "### Startup / Import Probes",
+                      "",
+                      "| Probe | Median (s) | First (s) | CPU Median (s) |",
+                      "|---|---:|---:|---:|",
+                  ]
+              )
+              for probe in startup_probes:
+                  stats = probe.get("stats_seconds", {})
+                  cpu_stats = probe.get("child_cpu_stats_seconds", {})
+                  lines.append(
+                      "| "
+                      f"{probe.get('name', '')} | "
+                      f"{float(stats.get('median', 0.0)):.4f} | "
+                      f"{float(probe.get('first_seconds', 0.0)):.4f} | "
+                      f"{float(cpu_stats.get('median', 0.0)):.4f} |"
+                  )
+              lines.append("")
+
+          lines.extend(
+              [
+                  "### Scenarios",
+                  "",
+                  "| Scenario | Median (s) | p95 (s) | CPU Median (s) | Files A/C | Artifacts KiB | Exit | Deterministic | Digest |",
+                  "|---|---:|---:|---:|---:|---:|---|:---:|---|",
+              ]
+          )
+
           for scenario in scenarios:
               stats = scenario.get("stats_seconds", {})
+              cpu_stats = scenario.get("child_cpu_stats_seconds", {})
+              inventory = scenario.get("inventory_sample", {})
               lines.append(
                   "| "
                   f"{scenario.get('name', '')} | "
                   f"{float(stats.get('median', 0.0)):.4f} | "
                   f"{float(stats.get('p95', 0.0)):.4f} | "
-                  f"{float(stats.get('stdev', 0.0)):.4f} | "
+                  f"{float(cpu_stats.get('median', 0.0)):.4f} | "
+                  f"{inventory.get('analyzed', 0)}/{inventory.get('cached', 0)} | "
+                  f"{float(scenario.get('artifact_total_kib_sample', 0.0)):.1f} | "
+                  f"{scenario.get('exit_code_counts', {})} | "
                   f"{'yes' if bool(scenario.get('deterministic')) else 'no'} | "
                   f"{scenario.get('digest', '')} |"
               )

.github/workflows/docs.yml

@@ -39,7 +39,7 @@ jobs:
         uses: actions/configure-pages@v5
 
       - name: Build docs site
-        run: uv run --with zensical==0.0.43 zensical build --clean --strict
+        run: uv run --with zensical==0.0.46 zensical build --clean --strict
 
       - name: Generate sample report artifacts
         run: uv run python scripts/build_docs_example_report.py --output-dir site/examples/report/live

.github/workflows/validation-corpus.yml

@@ -0,0 +1,92 @@
+name: validation-corpus
+run-name: validation corpus • ${{ github.event_name }} • ${{ github.ref_name }}
+
+on:
+  push:
+    branches: [ "**" ]
+  pull_request:
+  workflow_dispatch:
+    inputs:
+      tier:
+        description: Corpus tier
+        required: true
+        default: all
+        type: choice
+        options:
+          - smoke
+          - gates
+          - full
+          - all
+      corpus-ref:
+        description: codeclone-validation-corpus ref
+        required: true
+        default: main
+
+permissions:
+  contents: read
+
+concurrency:
+  group: validation-corpus-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  validation-corpus:
+    name: corpus
+    runs-on: ubuntu-latest
+    timeout-minutes: 20
+
+    steps:
+      - name: Checkout CodeClone
+        uses: actions/checkout@v6.0.2
+
+      - name: Checkout validation corpus
+        uses: actions/checkout@v6.0.2
+        with:
+          repository: orenlab/codeclone-validation-corpus
+          ref: ${{ github.event_name == 'workflow_dispatch' && inputs.corpus-ref || 'main' }}
+          path: validation-corpus
+
+      - name: Set up Python
+        uses: actions/setup-python@v6.2.0
+        with:
+          python-version: "3.14"
+          allow-prereleases: true
+
+      - name: Set up uv
+        uses: astral-sh/setup-uv@v5
+        with:
+          enable-cache: true
+
+      - name: Install CodeClone from this checkout
+        run: uv sync --all-extras
+
+      - name: Install validation corpus dependencies
+        run: uv sync --project validation-corpus
+
+      - name: Resolve corpus tier
+        shell: bash
+        run: |
+          tier="all"
+          if [ "${{ github.event_name }}" = "workflow_dispatch" ]; then
+            tier="${{ inputs.tier }}"
+          fi
+          echo "CORPUS_TIER=$tier" >> "$GITHUB_ENV"
+
+      - name: Run validation corpus
+        run: |
+          uv run --project validation-corpus python -m corpus_tools.cli \
+            --tier "$CORPUS_TIER" \
+            --codeclone-command "$GITHUB_WORKSPACE/.venv/bin/python -m codeclone.main" \
+            --work-root "$RUNNER_TEMP/codeclone-validation-corpus-work"
+
+      - name: Write summary
+        if: always()
+        shell: bash
+        run: |
+          {
+            echo "## CodeClone validation corpus"
+            echo
+            echo "- Tier: \`${CORPUS_TIER:-unknown}\`"
+            echo "- Corpus: \`orenlab/codeclone-validation-corpus\`"
+            echo "- CodeClone source: current checkout"
+          } >> "$GITHUB_STEP_SUMMARY"

.gitignore

@@ -52,3 +52,5 @@ extensions/vscode-codeclone/node_modules
 /coverage.json
 /benchmarks/memory_semantic_eval.md
 /scripts/commit_memory_phases.sh
+/extensions/jetbrains-codeclone/
+/issues/

AGENTS.md

@@ -156,7 +156,7 @@ If you touched baseline/cache/report contracts or CLI/MCP audit surfaces, also e
 If you touched `docs/`, `zensical.toml`, docs publishing workflow, or sample-report generation, also run:
 
 ```bash
-uv run --with zensical==0.0.43 zensical build --clean --strict
+uv run --with zensical==0.0.46 zensical build --clean --strict
 ```
 
 If you touched the MCP surface, also run: