First fully-green autonomous build: consolidated acceptance-gate + near-green + test-stability fix stack

packages/core/src/config/config.constants.ts

@@ -12,4 +12,5 @@ export const ENV_FLAG = {
   expertRescue: "TSFORGE_EXPERT_RESCUE",
   noNearGreenCheckpoint: "TSFORGE_NO_NEAR_GREEN_CHECKPOINT",
   noE2eAcceptance: "TSFORGE_NO_E2E_ACCEPTANCE",
+  noNearGreenRotation: "TSFORGE_NO_NEAR_GREEN_ROTATION",
 } as const;

packages/core/src/config/flags.ts

@@ -54,4 +54,13 @@ export const flags = {
    *  without knowing a flag exists. Kill-switch TSFORGE_NO_NEAR_GREEN_CHECKPOINT=1 disables
    *  it (A/B control / escape hatch). Thresholds N=2, M=3 from Phase 0a. */
   nearGreenCheckpoint: (): boolean => !isOn(ENV_FLAG.noNearGreenCheckpoint),
+  /** WS-B near-green ROTATION steer (#77): when the build sits at a near-green count but the
+   *  SPECIFIC error set rotates for several cycles (the model fixes one error and the fix spawns
+   *  another — e.g. extracts a component → its siblings/tests are now missing), inject a
+   *  completion-only steer ("finish the files that already have errors; don't create new
+   *  files/modules unless the same edit adds their siblings + tests"). This is the last-mile gap
+   *  that made green non-deterministic (build17 parked on it; build16 crossed by luck). Count-only
+   *  WS-B can't see it (the count never sprays). DEFAULT ON, deterministic (no network); kill with
+   *  TSFORGE_NO_NEAR_GREEN_ROTATION=1. Generic — keyed only on rule/file, no stack knowledge. */
+  nearGreenRotation: (): boolean => !isOn(ENV_FLAG.noNearGreenRotation),
 };

packages/core/src/loop/boringstack/acceptance/e2e-generator.ts

@@ -482,9 +482,14 @@ function generateNegativeBlocks(
   parentSeedingCode: string
 ): string {
   return entity.negatives
-    .map((neg) => {
-      // B2: Test title uses JSON.stringify to escape backticks/interpolation in neg.value
-      const testTitle = `negative: ${entity.id} rejects ${neg.field}=${neg.value}`;
+    .map((neg, index) => {
+      // B2: Test title uses JSON.stringify to escape backticks/interpolation in neg.value.
+      // The trailing [index] guarantees a UNIQUE title per negative: two negatives can share the
+      // same (field, value) — e.g. a required-field rule and a "must not be empty" mustNotHappen
+      // both yield name="" — and Playwright HARD-REJECTS a file with duplicate test titles (the
+      // whole spec fails to collect, ZERO tests run, and a green feature false-parks). parseStep
+      // matches on the "negative: " PREFIX, so the suffix does not affect result classification.
+      const testTitle = `negative: ${entity.id} rejects ${neg.field}=${neg.value} [${String(index)}]`;
 
       // Build valid field assignments (required non-FK fields)
       const validFieldAssignments = entity.fields
@@ -669,6 +674,28 @@ test.describe(${JSON.stringify(name)}, () => {
     await authedPage.dashboard.goto();
     await navigateTo${entity.id}(page);
 
+    // Capture WHY a create can silently fail: the api client throws on non-2xx and React Query
+    // swallows it into the mutation's error state, so the row just never appears with no clue.
+    // Record failed /api/ responses + console errors and append them to the assertion failure,
+    // turning "row not found" into the actual cause (e.g. "POST /api/v1/${entity.key} -> 422 ...").
+    const apiFailures${entity.id} = [];
+    page.on("response", (r) => {
+      const u = r.url();
+      const method = r.request().method();
+      // Record every mutation (so we can tell "POST fired -> 201 but row didn't render" from
+      // "no POST fired at all"), plus any non-2xx.
+      const isMutation = method === "POST" || method === "PATCH" || method === "DELETE";
+      if (u.includes("/api/") && (r.status() > 399 || isMutation)) {
+        void r
+          .text()
+          .then((b) => apiFailures${entity.id}.push(method + " " + new URL(u).pathname + " -> " + r.status() + " " + b.slice(0, 200)))
+          .catch(() => apiFailures${entity.id}.push(method + " " + new URL(u).pathname + " -> " + r.status()));
+      }
+    });
+    page.on("console", (m) => {
+      if (m.type() === "error") apiFailures${entity.id}.push("console.error: " + m.text().slice(0, 200));
+    });
+
     // Unique value → this test asserts on ITS OWN row (the shared DB accumulates rows
     // across tests/runs, so absolute row counts are unreliable).
     // Identity field gets the unique marker (type-aware: may not be the first field)
@@ -694,7 +721,14 @@ ${fillFirstFieldCode}    // Fill identity field with unique value
 
     // THIS test's row (identified by its unique value) appears — retries the async refetch
     const row = page.getByTestId("${ids.row}").filter({ hasText: unique });
-    await expect(row).toBeVisible({ timeout: 10000 });
+    try {
+      await expect(row).toBeVisible({ timeout: 10000 });
+    } catch (e) {
+      const cause = apiFailures${entity.id}.length > 0
+        ? "\\n\\nAPI activity + console during create (root-cause clue — if the POST is 2xx but the row is missing, the LIST/row render is the bug; if the POST is 4xx or absent, the mutation/form is):\\n" + apiFailures${entity.id}.join("\\n")
+        : "\\n\\n(No API mutation fired at all — the create form's submit is not wired to the create mutation, or the row renders without the unique text / without data-testid='${ids.row}'.)";
+      throw new Error((e instanceof Error ? e.message : String(e)) + cause);
+    }
 
     // Verify the shown cells render the created values (scoped to THIS row only)
 ${rowCellAssertions}

packages/core/src/loop/boringstack/acceptance/e2e-runner.ts

@@ -514,6 +514,13 @@ export function makeBoringstackAcceptanceRunner(exec: Exec): IAcceptanceRunner {
             ...process.env,
             PLAYWRIGHT_PORT: uiPort,
             VITE_API_BASE: ctx.apiBase,
+            // The dockerized ui-dev already serves the app on uiPort; Playwright MUST reuse it,
+            // never start its own host dev server. The scaffold's webServer.command is `bun run dev`,
+            // whose preflight-host-dev.sh HARD-EXITS 1 while the container is up — so if reuse is
+            // off (the config gates it on !CI, and a CI=1 build env flips it off) Playwright spawns
+            // that, exits 1 with ZERO tests run, and the harness reads a green feature as a failed
+            // acceptance → park. Forcing reuse ON makes Playwright attach to the running server.
+            PLAYWRIGHT_REUSE_SERVER: "true",
           };
 
           const result = await exec(
@@ -595,6 +602,13 @@ export function makeBoringstackAcceptanceRunner(exec: Exec): IAcceptanceRunner {
             ...process.env,
             PLAYWRIGHT_PORT: uiPort,
             VITE_API_BASE: ctx.apiBase,
+            // The dockerized ui-dev already serves the app on uiPort; Playwright MUST reuse it,
+            // never start its own host dev server. The scaffold's webServer.command is `bun run dev`,
+            // whose preflight-host-dev.sh HARD-EXITS 1 while the container is up — so if reuse is
+            // off (the config gates it on !CI, and a CI=1 build env flips it off) Playwright spawns
+            // that, exits 1 with ZERO tests run, and the harness reads a green feature as a failed
+            // acceptance → park. Forcing reuse ON makes Playwright attach to the running server.
+            PLAYWRIGHT_REUSE_SERVER: "true",
           };
 
           const result = await exec(

packages/core/src/loop/boringstack/acceptance/testid-contract.ts

@@ -84,7 +84,7 @@ ${entity.fields.map((f) => `  - \`data-testid="${ids.field(f.name)}"\` for the "
 ${entity.shows.map((s) => `  - \`data-testid="${ids.rowCell(s)}"\` for the "${s}" column`).join("\n")}
 - **Row edit button**: \`data-testid="${ids.rowEdit}"\` — the edit action on each row
 - **Row delete button**: \`data-testid="${ids.rowDelete}"\` — the delete action on each row
-- **Delete confirmation dialog**: \`data-testid="${ids.confirmDelete}"\` — the confirmation prompt when deleting a record
+- **Delete confirm button**: \`data-testid="${ids.confirmDelete}"\` — put this on the BUTTON that actually performs the deletion (the one whose click fires the delete mutation), NOT on the dialog container/overlay. End-to-end acceptance CLICKS this testid to confirm the delete; if it sits on a wrapper \`<div>\` the click hits the backdrop, the delete never fires, and the row stays (delete acceptance fails).
 ${
   entity.parents.length > 0
     ? `- **Relationship selectors**: \`data-testid\` for each parent entity select:\n${entity.parents.map((p) => `  - \`data-testid="${ids.field(p.fkField)}"\` for selecting a ${p.key}`).join("\n")}`
@@ -101,7 +101,7 @@ ${
 - Create button: add \`data-testid="${ids.create}"\` to the button that opens the form
 - Form component: add \`data-testid="${ids.form}"\` to the \`<form>\`, \`data-testid="${ids.submit}"\` to the submit button, and \`data-testid="${ids.field("...")}\` to each input
 - Table rows: add \`data-testid="${ids.row}"\` to each row container, \`data-testid="${ids.rowCell("...")}\` to data cells, \`data-testid="${ids.rowEdit}"\` and \`data-testid="${ids.rowDelete}"\` to action buttons
-- Delete confirmation: add \`data-testid="${ids.confirmDelete}"\` to the confirmation dialog
+- Delete confirmation: add \`data-testid="${ids.confirmDelete}"\` to the CONFIRM BUTTON inside the delete dialog — the button whose \`onClick\` fires the delete mutation. NOT the dialog wrapper/overlay \`<div>\`: acceptance CLICKS this testid to confirm, and clicking a wrapper hits the backdrop, so the delete never runs and the row is never removed.
 
 **Complete contract** (${required.length} required IDs):
 ${required.map((id) => `- \`${id}\``).join("\n")}

packages/core/src/loop/boringstack/build-config.ts

@@ -1,4 +1,25 @@
 import type { ExecutionMode } from "../prompt";
+import type { IPolicyRules } from "../../policy";
+
+/**
+ * Commands the model must NEVER run during a BoringStack build. The browser end-to-end
+ * acceptance is HARNESS-owned (run automatically after the fast gate, with the right port +
+ * server reuse). If the model runs it itself — `playwright`, `bun run dev`, `vite`, `dev.sh` —
+ * it starts a second host dev server that the scaffold's `preflight-host-dev.sh` guard
+ * HARD-EXITS 1 (the dockerized dev server already holds the port). That is an infra guard, not
+ * a code error: the model can't fix it, loops on it, and PARKS a feature whose code is already
+ * green (observed across build22–24, all 4 slices). Guidance alone did not stop it, so this is a
+ * deterministic policy DENY on the model's shell tool. It does NOT affect the harness's own
+ * acceptance run, which uses a separate injected exec, not the policy-gated `run` tool.
+ */
+const NO_BROWSER_E2E_DENY: IPolicyRules = {
+  deny: [
+    {
+      kind: "shell",
+      commandPattern: "playwright|\\bvite\\b|\\bbun\\s+run\\s+dev\\b|dev\\.sh",
+    },
+  ],
+};
 
 /**
  * The BoringStack build's fixed Session flags — spread into `Session.create` by the
@@ -17,6 +38,7 @@ export const BORINGSTACK_BUILD_SESSION: {
   readonly guidance: string;
   readonly pullConventions: true;
   readonly offerCheck: true;
+  readonly policyRules: IPolicyRules;
 } = {
   executionMode: "drive-to-green",
   guidance:
@@ -27,4 +49,5 @@ export const BORINGSTACK_BUILD_SESSION: {
     "is locked.",
   pullConventions: true,
   offerCheck: true,
+  policyRules: NO_BROWSER_E2E_DENY,
 };

packages/core/src/loop/boringstack/build.ts

@@ -118,6 +118,15 @@ export const APP_SIDEBAR_FILE =
  *  its feature's route entry, never modify another feature's route. */
 export const APP_ROUTES_FILE = "apps/ui/src/app/router/routes.tsx";
 
+/** The sidebar's co-located test. It asserts the EXACT number of nav links, so the moment a
+ *  feature adds its NavLink (required for reachability) the count changes and this test fails at
+ *  the FINAL full-project validate (the fast per-feature gate doesn't run the vitest suite, so it
+ *  only surfaces there → a fully-verified feature still leaves the build "stuck"). The scaffold is
+ *  an external clone we can't edit, so the model must keep this test in sync: scope it in and
+ *  instruct (refinePrompt) to bump the expected link count by its one added link — nothing else. */
+export const APP_SIDEBAR_TEST_FILE =
+  "apps/ui/src/components/core/AppSidebar/AppSidebar.test.tsx";
+
 export function scopeFor(name: string): string[] {
   const camel = toCamelCase(name);
 
@@ -136,6 +145,9 @@ export function scopeFor(name: string): string[] {
     // to the router. Add-only: the model may ADD its feature's entry, never modify others'.
     APP_SIDEBAR_FILE,
     APP_ROUTES_FILE,
+    // Co-located sidebar test asserts the exact nav-link count; adding a NavLink changes it, so
+    // the model must be able to bump the count (see APP_SIDEBAR_TEST_FILE).
+    APP_SIDEBAR_TEST_FILE,
   ];
 }
 

packages/core/src/loop/boringstack/refine-prompt.ts

@@ -195,7 +195,7 @@ then in the component body \`const editHandler = makeIdHandler(onEdit);\` (and \
 
 **Every visible string via \`t("features.${camel}.<key>")\`** — no hardcoded JSX text (button labels like "Edit"/"Delete" included).
 
-**Make the feature reachable.** Add a sidebar link to \`apps/ui/src/components/core/AppSidebar/AppSidebar.tsx\` (add your feature's entry to the \`APP_SIDEBAR_NAV_ITEMS\` array, following the existing format) and register its route in \`apps/ui/src/app/router/routes.tsx\` (add a route pointing at your feature's page component). Both files are in your editable scope — ADD ONLY your feature's entries, never modify another feature's link/route (same rule as the shared schema + locale files). A feature missing from the sidebar or router is unreachable and fails browser acceptance.
+**Make the feature reachable.** Add a sidebar link to \`apps/ui/src/components/core/AppSidebar/AppSidebar.tsx\` (add your feature's entry to the \`APP_SIDEBAR_NAV_ITEMS\` array, following the existing format) and register its route in \`apps/ui/src/app/router/routes.tsx\` (add a route pointing at your feature's page component). Both files are in your editable scope — ADD ONLY your feature's entries, never modify another feature's link/route (same rule as the shared schema + locale files). A feature missing from the sidebar or router is unreachable and fails browser acceptance. **After adding your NavLink, update the sidebar's co-located test \`apps/ui/src/components/core/AppSidebar/AppSidebar.test.tsx\`: it asserts the EXACT number of nav links (e.g. \`toHaveLength(6)\`), so bump that count by exactly one for your added link — otherwise the final full-project validate fails even though your feature is correct.**
 
 ---
 
@@ -240,6 +240,16 @@ WRONG \`tsc\` that prints "This is not the tsc command you are looking for". NEV
 \`npx\`/\`npm\`/\`yarn\` — this stack is bun-only. If you ever must run something else, use
 the project's \`bun run <script>\`.
 
+## Do NOT run the browser end-to-end acceptance yourself
+The harness runs the full browser (Playwright) acceptance AUTOMATICALLY after the fast gate is
+green — it is NOT your job. Do NOT run \`playwright\`/\`bunx playwright test\`, \`bun run dev\`,
+\`vite\`, or \`dev.sh\`. The dockerized dev server is already serving the app; starting a second one
+on the host is HARD-REFUSED by the \`preflight-host-dev.sh\` guard (exit 1) — that is an
+infrastructure guard, NOT a code error, and trying to "fix" it will trap you in a dead loop that
+burns the whole turn budget and parks a feature whose code is already correct. When the \`check\`
+tool returns \`passed: true\` and your required \`data-testid\`s are present, you are DONE — STOP
+there and let the harness verify the browser flow.
+
 ---
 
 Begin implementation now.`;