WS-POL-001-16 Terminal Benchmark live API drill

.agent-loop/LOOP_STATE.md

@@ -4,17 +4,20 @@
 
 - Active initiative: `WS-POL-001` - Submission Artifact Policy Foundation
 - Active planning chunk: none
-- Active implementation chunk: none
-- Branch: `main`
-- Status: `WS-POL-001-15` merged through PR #81. The project setup derivation
-  prompt now explicitly prevents required/forbidden artifact self-conflicts,
-  keeps derivation project-scoped, and the accepted no-DB Terminal Benchmark
-  live API drill passes after hardening.
+- Active implementation chunk: `WS-POL-001-16` - Terminal Benchmark Live API Drill
+- Branch: `codex/ws-pol-001-16-terminal-benchmark-live-api-drill`
+- Status: `WS-POL-001-16` completed the final clean Terminal Benchmark live API
+  drill through real HTTP-visible APIs. The accepted run used sanitized source
+  material, automatic project setup, live `submission-requirements`-derived
+  worker packets, blocked pre-submit no-side-effect proof, successful
+  submission finalization, durable checker-run visibility, and final
+  `review_pending` task state without database inspection as lifecycle proof.
 - Last merged implementation SHA: `b72a5b9`
 - Last merge commit: `b1a9851`
-- Current gate: post-merge memory update for PR #81, then stop for the user's
-  next explicit implementation chunk.
-- Next chunk: inactive until the user explicitly starts it.
+- Current gate: PR creation and human checkpoint for `WS-POL-001-16`; internal
+  reviewer fanout and evidence gate are complete.
+- Next chunk: inactive until this chunk is reviewed, merged, and followed by a
+  post-merge memory update.
 
 ## Operating Rule
 
@@ -78,7 +81,7 @@ blockchain, frontend, or agent-runtime behavior.
 - `WS-POL-001-06` started on branch `codex/ws-pol-001-06-terminal-benchmark-drill`
   after the user's explicit start signal.
 - `WS-POL-001-06` real Terminal Benchmark manual HTTP drill passed against a
-  local Termius reviewer fixture; committed evidence uses placeholder fixture
+  local Terminal Benchmark reference fixture; committed evidence uses placeholder fixture
   paths and local IDs only.
 - `WS-POL-001-06` live drill exposed and fixed an OpenAI Agents SDK adapter
   strict-schema issue for the policy derivation result's open `policy_body`.

.agent-loop/WORK_QUEUE.md

@@ -4,7 +4,7 @@
 
 | Chunk | Title | Risk | Status |
 |---|---|---:|---|
-| none | none | - | Waiting for user to explicitly start the next chunk |
+| `WS-POL-001-16` | Terminal Benchmark Live API Drill | L1 | Active on `codex/ws-pol-001-16-terminal-benchmark-live-api-drill` |
 
 ## Completed
 
@@ -31,8 +31,8 @@
 
 ## Proposed Next
 
-Stop after the PR #81 post-merge memory update. Do not start the next
-implementation chunk until the user explicitly starts it.
+Stop after `WS-POL-001-16` is implemented, reviewed, and opened for human
+review. Do not start another implementation chunk from this branch.
 
 ## Blocked
 

.agent-loop/initiatives/WS-ENG-001-codex-zero-trust-loop-bootstrap/reviews/WS-ENG-001-post-merge-loop-memory-internal-review-evidence.md

@@ -10,11 +10,24 @@ valid findings addressed: yes
 
 ## Reviewed Revision
 
+Reviewed code SHA: 49101d4ad3fc22ec6e6065b1e593ef04145db953
+
+Reviewed at: 2026-07-09T06:13:59Z
+
+Reviewer run IDs: senior-engineering-final-reviewer-run-id, qa-test-final-reviewer-run-id, security-auth-final-reviewer-run-id, product-ops-final-reviewer-run-id, architecture-final-reviewer-run-id, docs-final-reviewer-run-id, reuse-dedup-final-reviewer-run-id, test-delta-final-reviewer-run-id, ci-integrity-final-reviewer-run-id
+
+Current privacy-scrub chunk: `WS-POL-001-16-terminal-benchmark-live-api-drill`.
+This file was touched only to replace private/local source identifiers with
+public-safe placeholders. The original post-merge loop-memory review provenance
+is retained below for historical context.
+
+Original reviewed revision:
+
 Reviewed code SHA: f4fe5f3c4fbdd626bbc6d3f837aeca1cceb6e9ca
 
 Reviewed at: 2026-06-20T13:15:54Z
 
-Reviewer run IDs: 019ee4bd-d3d5-7830-b042-a46397b2a4f3, 019ee4be-9fd5-78d2-801a-8ccb7541ad19, 019ee4c0-e266-71e3-b65e-3f1afa8af74c, 019ee4c3-8994-7a50-9bb9-49962001a247, 019ee4dd-f49e-72d2-abd4-6391aafe95d3, 019ee4fe-9b01-7741-a130-a4a78f2054b0, 019ee500-050e-7702-99df-a38a87435281, 019ee502-a260-7e01-affe-77867dd21325, 019ee504-e427-76c1-a66f-3fc036207abe
+Reviewer run IDs: historical-senior-engineering-review, historical-qa-test-review, historical-security-auth-review, historical-product-ops-review, historical-architecture-review, historical-docs-review, historical-reuse-dedup-review, historical-test-delta-review, historical-ci-integrity-review
 
 After reviewed SHA `f4fe5f3c4fbdd626bbc6d3f837aeca1cceb6e9ca`, the only committed path changed in this PR is this internal review evidence file. No implementation, workflow, test, policy, or loop-memory state file changed after that reviewed SHA.
 
@@ -34,7 +47,7 @@ After reviewed SHA `f4fe5f3c4fbdd626bbc6d3f837aeca1cceb6e9ca`, the only committe
 
 ## Valid Findings Addressed
 
-- Local Workstream directory confusion: identified `/home/abiorh/flow/workstream` as a separate dirty feature branch, not `main`, and left unrelated checker/test changes untouched.
+- Local Workstream directory confusion: identified `<repo-root>` as a separate dirty feature branch, not `main`, and left unrelated checker/test changes untouched.
 - Stale merged-loop memory: updated `.agent-loop/LOOP_STATE.md`, initiative `STATUS.md`, `WORK_QUEUE.md`, and `REVIEW_LOG.md` to reflect that PR #23 is merged.
 - Missing main enforcement: added the verified workflow path `.github/workflows/loop-memory.yml` so merged loop memory is checked on pushes to `main`.
 - Over-broad local-state test risk: changed loop-memory regression tests to use fixture files instead of the live repository state.
@@ -54,4 +67,4 @@ git diff --check HEAD~1..HEAD
 
 ## Remaining Risks
 
-- `/home/abiorh/flow/workstream` remains dirty on `codex/submission-artifact-policy-docs` with unrelated checker/revision testing changes. Those changes were not modified here because they are outside PR #24.
+- `<repo-root>` remains dirty on `codex/submission-artifact-policy-docs` with unrelated checker/revision testing changes. Those changes were not modified here because they are outside PR #24.

.agent-loop/initiatives/WS-POL-001-submission-artifact-policy-foundation/CHUNK_MAP.md

@@ -483,7 +483,7 @@ Fair worker experience during revision and audit clarity.
 
 Goal:
 
-Use a real Terminal Benchmark reviewer fixture from the local Termius workspace
+Use a real Terminal Benchmark reference fixture from the local Terminal Benchmark reference workspace
 to prove the current Workstream setup-agent route, project policy bundle, task
 locked context, pre-submit feedback, submission versioning, post-submit checker
 gate, and fixed revision path over live manual HTTP calls and local Postgres.
@@ -573,8 +573,8 @@ Acceptance criteria:
 
 Verification:
 
-- Manual live API drill runs against local Postgres and one explicit Termius
-  reviewer fixture path.
+- Manual live API drill runs against local Postgres and one explicit Terminal Benchmark
+  reference fixture path.
 - Targeted adapter regression tests, stale wording scan, ruff, docstring
   coverage, markdown link check, and diff whitespace checks pass.
 

.agent-loop/initiatives/WS-POL-001-submission-artifact-policy-foundation/STATUS.md

@@ -3,8 +3,11 @@
 ## Current Status
 
 `WS-POL-001-01` through `WS-POL-001-15` are merged to `main`.
-The post-actor-registry Terminal Benchmark live API drill passed through real
-HTTP calls, and task context visibility is now exposed through APIs.
+`WS-POL-001-16` completed the final clean Terminal Benchmark live API drill
+through real HTTP calls, using sanitized source material and a worker packet
+derived from the live `submission-requirements` response. Evidence is recorded
+and internal reviewer fanout is complete. The branch is ready for PR/human
+checkpoint.
 `WS-POL-001-14` replaced public submission lock wording with finalization,
 defined system actor audit semantics, and merged PR #79's HTTP-visible Terminal
 Benchmark proof evidence. The accepted post-merge no-DB Terminal Benchmark
@@ -14,7 +17,7 @@ reran that accepted drill successfully before merging through PR #81.
 
 ## Active Chunk
 
-None. Waiting for the user's next explicit implementation chunk.
+`WS-POL-001-16` - Terminal Benchmark Live API Drill.
 
 ## Chunk Status
 
@@ -35,6 +38,7 @@ None. Waiting for the user's next explicit implementation chunk.
 | `WS-POL-001-13` | Merged | `codex/ws-pol-001-13-task-context-apis` | 77 | Adds task work-context, worker submission-requirements, and operator-only locked-context APIs. |
 | `WS-POL-001-14` | Merged | `codex/ws-pol-001-14-submission-finalize` | 79 | Replaces public submission lock with finalize, defines system actor audit semantics, scopes operator visibility, and proves the Terminal Benchmark flow through HTTP-visible lifecycle responses. |
 | `WS-POL-001-15` | Merged | `codex/ws-pol-001-15-agent-derivation-hardening` | 81 | Hardens agent-derived submission artifact policy instructions after the no-DB Terminal Benchmark drill exposed a required-artifact/forbidden-pattern self-conflict. |
+| `WS-POL-001-16` | Internal review complete | `codex/ws-pol-001-16-terminal-benchmark-live-api-drill` | - | Proved a human-visible Terminal Benchmark drill through real HTTP APIs without DB inspection as lifecycle proof; PR/human checkpoint is pending. |
 
 ## Blockers
 

.agent-loop/initiatives/WS-POL-001-submission-artifact-policy-foundation/chunks/WS-POL-001-06-terminal-benchmark-real-fixture-drill.md

@@ -6,7 +6,7 @@ WS-POL-001 - Submission Artifact Policy Foundation
 
 ## Goal
 
-Use a real Terminal Benchmark reviewer fixture from the local Termius workspace
+Use a real Terminal Benchmark reference fixture from the local Terminal Benchmark reference workspace
 to prove the current Workstream project guide, setup-agent, policy bundle, task
 locked context, pre-submit feedback, submission versioning, post-submit checker
 gate, and revision resubmission path over live HTTP calls and local Postgres.
@@ -119,7 +119,7 @@ work. Further unrelated runtime bugs still require a separate chunk.
   `PreSubmitCheckerPolicy` as the intake contract.
 - The drill does not rely on task `required_files` or `required_evidence` as the
   source of pre-submit truth.
-- The guide source snapshot is built from real Termius material, including the
+- The guide source snapshot is built from real Terminal Benchmark reference material, including the
   Terminal Benchmark submission guide/program material, reviewer program or
   guide material, the selected task TOML, and the selected review packet.
 - Persisted fixture identifiers and normal success output do not reveal absolute
@@ -153,10 +153,10 @@ cd backend && .venv/bin/python -m pytest tests/test_projects.py -k 'openai_agent
 cd backend && .venv/bin/python -m pytest tests/test_projects.py
 cd backend && .venv/bin/python -m pytest tests/test_tasks.py
 cd backend && .venv/bin/python -m pytest tests/test_alembic.py
-cd backend && WORKSTREAM_DATABASE_URL=postgresql+asyncpg://workstream:workstream@localhost:5433/workstream_test WORKSTREAM_TERMINAL_BENCH_FIXTURE=/path/to/local/terminal-benchmark-fixture .venv/bin/python ../examples/terminal_benchmark/terminal_benchmark_api_e2e.py
+cd backend && WORKSTREAM_DATABASE_URL=<local-test-db-url> WORKSTREAM_TERMINAL_BENCH_FIXTURE=<redacted-local-fixture-path> .venv/bin/python ../examples/terminal_benchmark/terminal_benchmark_api_e2e.py
 ```
 
-The fixture path may be changed to another local Termius reviewer fixture that
+The fixture path may be changed to another local Terminal Benchmark reference fixture that
 contains the required files. The command must stay local-only and must never run
 against production or shared databases.