test(workbench): add native CLI live qualification

.github/workflows/rust.yml

@@ -51,6 +51,7 @@ jobs:
             scripts/workbench/pre423_contract_ledger.py \
             scripts/workbench/workbench_contract.py \
             scripts/workbench/live_workbench.py \
+            scripts/workbench/native_cli_workbench.py \
             scripts/workbench/local_wal_recovery_gate.py \
             scripts/workbench/object_namespace_recovery_gate.py \
             scripts/workbench/restore_composition_gate.py \
@@ -59,6 +60,7 @@ jobs:
           python3 scripts/workbench/pre423_contract_ledger_test.py
           python3 scripts/workbench/workbench_contract_test.py
           python3 scripts/workbench/live_workbench_test.py
+          python3 scripts/workbench/native_cli_workbench_test.py
           python3 scripts/workbench/local_wal_recovery_gate_test.py
           python3 scripts/workbench/object_namespace_recovery_gate_test.py
           python3 scripts/workbench/restore_composition_gate_test.py
@@ -188,7 +190,7 @@ jobs:
                   --dependency "etcd=sha256:e8cd3fa8064c98137c5dbd78b76f969417ace84efb83c481041d7a52ffdd8fb9"
                   --dependency "object-store=oci:rustfs/rustfs@sha256:e620d37756fff072b10bf648c7bb9d370d7e91a928b7e6a5e1ac85bdfb4e4dab"
                   --evidence "qualification=$evidence_root/qualification.json"
-                  --evidence "mcp-transcript=$evidence_root/mcp-transcript.jsonl"
+                  --evidence "cli-transcript=$evidence_root/cli-transcript.jsonl"
                 )
                 producer_args+=(
                   --nokv-bin "$product_binary"
@@ -532,6 +534,78 @@ jobs:
           if-no-files-found: error
           retention-days: 7
 
+      - name: Qualify primary native CLI Workbench contracts
+        id: native_cli_workbench
+        shell: bash
+        env:
+          NATIVE_CLI_WORKBENCH_ROOT: ${{ runner.temp }}/native-cli-workbench
+        run: |
+          set -euo pipefail
+          endpoint=http://127.0.0.1:22381
+          peer=http://127.0.0.1:22382
+          mkdir -p "$NATIVE_CLI_WORKBENCH_ROOT"
+          etcd \
+            --name nokv-native-cli-workbench \
+            --data-dir "$NATIVE_CLI_WORKBENCH_ROOT/etcd-data" \
+            --listen-client-urls "$endpoint" \
+            --advertise-client-urls "$endpoint" \
+            --listen-peer-urls "$peer" \
+            --initial-advertise-peer-urls "$peer" \
+            --initial-cluster "nokv-native-cli-workbench=$peer" \
+            --initial-cluster-state new \
+            --log-level warn \
+            >"$NATIVE_CLI_WORKBENCH_ROOT/etcd.log" 2>&1 &
+          etcd_pid=$!
+          trap 'kill "$etcd_pid" >/dev/null 2>&1 || true; wait "$etcd_pid" >/dev/null 2>&1 || true' EXIT
+          ready=false
+          for _ in $(seq 1 60); do
+            if etcdctl --endpoints "$endpoint" endpoint health >/dev/null 2>&1; then
+              ready=true
+              break
+            fi
+            if ! kill -0 "$etcd_pid" >/dev/null 2>&1; then
+              break
+            fi
+            sleep 0.25
+          done
+          if [[ "$ready" != true ]]; then
+            cat "$NATIVE_CLI_WORKBENCH_ROOT/etcd.log"
+            exit 1
+          fi
+          python3 scripts/workbench/native_cli_workbench.py \
+            --nokv-bin target/debug/nokv \
+            --evidence-dir "$NATIVE_CLI_WORKBENCH_ROOT/evidence" \
+            --metadata-dir "$NATIVE_CLI_WORKBENCH_ROOT/metadata" \
+            --root-id 55555555555555555555555555555555 \
+            --agent-id 88888888888888888888888888888888 \
+            --agent-name ci-native-cli-agent \
+            --logical-shard-id 66666666666666666666666666666666 \
+            --etcd-endpoint "$endpoint" \
+            --etcd-key-prefix "/nokv/control/native-cli-${GITHUB_RUN_ID}-${GITHUB_RUN_ATTEMPT}" \
+            --server-bind 127.0.0.1:17751 \
+            --advertise-endpoint 127.0.0.1:17751 \
+            --object-endpoint http://127.0.0.1:9000 \
+            --object-bucket nokv-local-wal-recovery-gate \
+            --object-root "native-cli-${GITHUB_RUN_ID}-${GITHUB_RUN_ATTEMPT}" \
+            --object-access-key-id rustfsadmin \
+            --object-secret-access-key rustfsadmin \
+            --command-timeout-seconds 45
+          jq -e '.workbench_workflow.status == "PASS"' \
+            "$NATIVE_CLI_WORKBENCH_ROOT/evidence/qualification.json"
+          jq -e '.workbench_workflow.transport == "native-cli"' \
+            "$NATIVE_CLI_WORKBENCH_ROOT/evidence/qualification.json"
+          jq -e '.acceptance_gates["0"].status == "NOT QUALIFIED"' \
+            "$NATIVE_CLI_WORKBENCH_ROOT/evidence/qualification.json"
+
+      - name: Upload native CLI Workbench evidence
+        if: ${{ always() && steps.native_cli_workbench.outcome != 'skipped' }}
+        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a
+        with:
+          name: native-cli-workbench-${{ github.sha }}
+          path: ${{ runner.temp }}/native-cli-workbench
+          if-no-files-found: error
+          retention-days: 7
+
       - name: Qualify restored Workbench composition
         id: restore_composition
         shell: bash

Makefile

@@ -39,6 +39,7 @@ workbench-test:
 	python3 scripts/workbench/pre423_contract_ledger_test.py
 	python3 scripts/workbench/workbench_contract_test.py
 	python3 scripts/workbench/live_workbench_test.py
+	python3 scripts/workbench/native_cli_workbench_test.py
 
 governance-test:
 	python3 scripts/ci/pr_change_governance_test.py
@@ -58,6 +59,7 @@ verify:
 	python3 scripts/workbench/pre423_contract_ledger_test.py
 	python3 scripts/workbench/workbench_contract_test.py
 	python3 scripts/workbench/live_workbench_test.py
+	python3 scripts/workbench/native_cli_workbench_test.py
 	python3 scripts/ci/pr_change_governance_test.py
 	python3 scripts/release/test_homebrew_source_release.py
 	python3 scripts/release/test_python_sdk_release.py

bench/workbench-live/README.md

@@ -5,18 +5,22 @@ SPDX-License-Identifier: Apache-2.0
 
 # Live Workbench evidence
 
-The executable product-boundary workload lives at
-`scripts/workbench/live_workbench.py`. It exercises the flat `nokv`
-CLI-backed optional MCP sidecar against real root routing, Holt metadata
-ownership, and an S3-compatible object provider. It is sidecar qualification,
-not evidence that MCP is NoKV's primary integration surface. Its deterministic
-runtime evidence directory is under `target/workbench-live/evidence/` by
-default; evidence is not checked into this source directory.
+The primary executable product-boundary workload lives at
+`scripts/workbench/native_cli_workbench.py`. It exercises the full
+`nokv workbench <tool> <canonical-json>` CLI boundary against real root
+routing, Holt metadata ownership, and an S3-compatible object provider. Its
+deterministic runtime evidence directory is under
+`target/native-cli-workbench/evidence/` by default; evidence is not checked
+into this source directory.
 
-This is a correctness and interoperability workload, not a performance result.
-It records all 18 tool inputs and exact responses, one deliberate create-only
-error, commit replay, frozen reads, restore projections, and the explicit
-materialize/collect boundary. Missing external services are `NOT QUALIFIED`.
+`scripts/workbench/live_workbench.py` separately qualifies the optional MCP
+sidecar. It is not evidence that MCP is NoKV's primary integration surface.
+
+These are correctness and interoperability workloads, not performance results.
+The native runner records all 18 tool argv/input/result pairs, one deliberate
+create-only error, commit replay, frozen reads, restore projections, and the
+explicit materialize/collect boundary. Missing external services are
+`NOT QUALIFIED`.
 
 See `scripts/workbench/README.md` for commands and
 `docs/development/workspace-acceptance.md` for the qualification boundary.

docs/development/pre423-contract-ledger.md

@@ -195,7 +195,7 @@ typed producers pass.
 | `pre423_contract_ledger.py`, `workbench_contract_test.py`, and every `*_gate_test.py` | Validate policy, checker, or harness shape only. They sign no product stable ID by themselves. |
 | `cargo test -p nokv-agent` | Candidate `nokv-agent-unit` source for schema-surface `T01`-`T04`, `C01`, `C02`, `C07`, and `L01`. |
 | `cargo test -p nokv-agent --test sdk_facade` | Candidate `nokv-agent-unit` source for the ledger's facade-contract and output-golden scenarios. Each claim still needs a direct assertion-to-scenario mapping; the broad command is not one receipt for all IDs. |
-| `live_workbench.py` | Its explicit stable checks can back native scenarios for `T08`, `C04`, `C05`, and `C15`. Its `C06` probe proves same-name read/write isolation, reconnect, and wrong-agent admission, but does not yet cover every operation required by the `C06` root-authority scenario. It is raw MCP evidence, not LingTai evidence. |
+| `native_cli_workbench.py` | Its explicit direct-CLI checks can back native scenarios for `T08`, `C04`, `C05`, and `C15`. Its `C06` probe proves same-name read/write isolation, reconnect, and wrong-agent admission, but does not yet cover every operation required by the `C06` root-authority scenario. It is raw native CLI evidence, not LingTai evidence. |
 | `restore_composition_gate.py` | Can back restore-composition scenarios for `T14`, `T18`, `C20`, and `C21` where its exact A to snapshot A to B to snapshot B to C oracle asserts the scenario. It does not satisfy their independent provider, native, commit, output, or LingTai gates. |
 | `object_namespace_recovery_gate.py` | Can back the provider restart binding scenario in `C06` and the explicit object-outage read scenario in `C12`. Its commit replay, wrong-prefix, and exact-byte observations are partial evidence only for the remaining provider scenarios. |
 | `local_wal_recovery_gate.py` | Qualifies owner-epoch/local-WAL recovery, which is not one of the 47 pre-#423 stable IDs. It signs none of this ledger's scenarios. |
@@ -209,11 +209,11 @@ Workbench ledger qualification result.
 
 The five source-bound static or exact-test producers are implemented and have
 their own fail-closed policy tests. They still need to be executed as part of
-the complete protected producer graph. Three existing live harnesses need
-typed scenario/result/evidence integration without weakening their current
-oracles: `live-workbench`, `object-namespace-recovery`, and
-`restore-composition`. Three behavior boundaries still require dedicated
-commands before the ledger can reach `PASS`:
+the complete protected producer graph. The direct native CLI `live-workbench`
+producer now retains `cli-transcript` evidence; the object-namespace and
+restore-composition live harnesses still need typed scenario/result/evidence
+integration without weakening their current oracles. Three behavior boundaries
+still require dedicated commands before the ledger can reach `PASS`:
 
 1. `snapshot-lifecycle` integration must deterministically cover committed-only
    minting, frozen reads after live mutation, renew by id and alias, terminal

docs/development/workspace-acceptance.md

@@ -45,13 +45,17 @@ throughput, and p50/p95/p99/maximum latency.
 
 The scientific reconstruction workflow must exercise the complete 18-tool
 Workbench semantics through the primary native CLI boundary. The direct Python
-SDK must independently exercise its supported programmatic path. The existing
-black-box runner,
-[`scripts/workbench/live_workbench.py`](../../scripts/workbench/live_workbench.py),
+SDK must independently exercise its supported programmatic path. The black-box
+native runner,
+[`scripts/workbench/native_cli_workbench.py`](../../scripts/workbench/native_cli_workbench.py),
+starts the same product owner and invokes every tool as
+`nokv workbench <tool> <canonical-json>` in a fresh CLI process, retaining the
+exact CLI transcript. The existing
+[`scripts/workbench/live_workbench.py`](../../scripts/workbench/live_workbench.py)
 qualifies the optional MCP sidecar only. Its dry-run proves only command
 construction and tool coverage; a live run retains exact sidecar and process
-evidence. It cannot substitute for native CLI or Python SDK evidence. Absent
-etcd, S3-compatible storage, or the requested binary is `NOT QUALIFIED`, never
+evidence. Neither runner substitutes for the Python SDK path. Absent etcd,
+S3-compatible storage, or the requested binary is `NOT QUALIFIED`, never
 `PASS`.
 
 Required evidence:

scripts/workbench/README.md

@@ -22,11 +22,19 @@ The checked-in integration assets are deliberately small:
   exact Rust-owned schema at
   `crates/nokv-agent/workbench_contract_schema.json`.
 - `workbench_contract_test.py` tests normalization and exact surface matching.
-- `live_workbench.py` provisions one root, starts one explicit metadata
-  owner and the flat `nokv mcp` command, then records a real
-  scientific reconstruction workflow through all 18 tools.
-- `live_workbench_test.py` checks exact coverage/order, flat commands,
-  secret redaction, dry-run evidence, and fail-closed qualification.
+- `native_cli_workbench.py` provisions one root, starts one explicit metadata
+  owner, and records the scientific reconstruction workflow by invoking every
+  tool through the primary `nokv workbench <tool> <canonical-json>` CLI
+  boundary in a fresh process.
+- `native_cli_workbench_test.py` freezes direct-CLI argv construction, exact
+  tool coverage, transcript/error parsing, secret redaction, dry-run evidence,
+  and the required CI artifact.
+- `live_workbench.py` provisions one root, starts one explicit metadata owner
+  and the flat optional `nokv mcp` command, then records the same workflow
+  through the sidecar transport.
+- `live_workbench_test.py` checks the sidecar runner's exact coverage/order,
+  flat commands, secret redaction, dry-run evidence, and fail-closed
+  qualification.
 - `local_wal_recovery_gate.py` starts an isolated real etcd process and proves
   that a killed `Recovering(2)` owner is retried at epoch 2 both before and
   after the local Holt fence advances. It separately sends `SIGTERM` to a
@@ -65,7 +73,7 @@ The checked-in integration assets are deliberately small:
 
 The source-bound qualification manifest covers every producer declared by the
 pre-#423 ledger. Live producers bind the exact product binary, pinned dependency
-identities, and their required `qualification` and MCP-transcript evidence
+identities, and their required `qualification` and transport-transcript evidence
 roles. Missing LingTai and installed-Python live runners emit typed `NQ`
 receipts with a concrete gap reason. The native Workbench and object-namespace
 entrypoints also refuse to claim scenarios their bounded harnesses do not run.
@@ -83,6 +91,7 @@ python3 scripts/workbench/pre423_contract_ledger.py
 python3 scripts/workbench/pre423_contract_ledger_test.py
 python3 scripts/workbench/workbench_contract_test.py
 python3 scripts/workbench/live_workbench_test.py
+python3 scripts/workbench/native_cli_workbench_test.py
 python3 scripts/workbench/local_wal_recovery_gate_test.py
 python3 scripts/workbench/object_namespace_recovery_gate_test.py
 python3 scripts/workbench/restore_composition_gate_test.py
@@ -109,16 +118,49 @@ metadata schemas are rejected; the sole marker is `nokv_workspace`.
 
 ## Live Workbench evidence
 
-Dry-run validates the redacted command graph and exact 18-tool coverage without
-claiming that any dependency ran:
+### Primary native CLI
+
+Dry-run validates the redacted direct-CLI command graph and exact 18-tool
+coverage without claiming that any dependency ran:
+
+```bash
+python3 scripts/workbench/native_cli_workbench.py \
+  --dry-run \
+  --evidence-dir target/native-cli-workbench/evidence/dry-run
+```
+
+A live run consumes already-running etcd and S3-compatible services. Each
+Workbench call is a separate invocation of `nokv workbench`; the evidence
+records exact redacted argv, canonical JSON input, stdout, stderr, exit code,
+and the decoded public result in `cli-transcript.jsonl`.
+
+```bash
+python3 scripts/workbench/native_cli_workbench.py \
+  --build \
+  --root-id 11111111111111111111111111111111 \
+  --agent-id 44444444444444444444444444444444 \
+  --agent-name research-agent \
+  --logical-shard-id 22222222222222222222222222222222 \
+  --etcd-endpoint http://127.0.0.1:2379 \
+  --object-endpoint http://127.0.0.1:9000 \
+  --object-bucket nokv-workbench-live \
+  --metadata-mode create \
+  --metadata-dir target/native-cli-workbench/metadata/live-01 \
+  --evidence-dir target/native-cli-workbench/evidence/live-01
+```
+
+### Optional MCP sidecar
+
+The sidecar runner remains separate. Its dry-run validates the redacted command
+graph and exact 18-tool coverage without claiming that any dependency ran:
 
 ```bash
 python3 scripts/workbench/live_workbench.py \
   --dry-run \
   --evidence-dir target/workbench-live/evidence/dry-run
 ```
 
-A live run consumes already-running etcd and S3-compatible services.
+A live sidecar run consumes already-running etcd and S3-compatible services.
 Credentials may be supplied with `NOKV_LIVE_S3_ACCESS_KEY_ID` and
 `NOKV_LIVE_S3_SECRET_ACCESS_KEY`; evidence records only their presence and
 redacts secret values without retaining a digest verifier.
@@ -163,10 +205,12 @@ record size, so a long-lived deployment such as a partner pre-pilot should run
 recovery authority, nothing is published, and `--metadata-recover-log` is not
 available for that shard.
 
-The deterministic evidence directory contains `plan.json`, exact paired
-requests/responses in `mcp-transcript.jsonl`, `processes.jsonl` and process
-logs, build/config facts in `environment.json`, validated schema evidence in
-`contract.json`, and explicit statuses in `qualification.json`.
+The native deterministic evidence directory contains `plan.json`, exact direct
+CLI invocations in `cli-transcript.jsonl`, `processes.jsonl` and process logs,
+build/config facts in `environment.json`, the binary-exported 18-tool schema
+check in `contract.json`, and explicit statuses in `qualification.json`. The
+sidecar runner separately retains paired JSON-RPC requests/responses in
+`mcp-transcript.jsonl` and its MCP schema evidence.
 
 Exit status `3` means a required live dependency is absent and the workflow is
 `NOT QUALIFIED`, never a pass. Exit status `2` means a configured live boundary