test(pty): pin spawned claude to EVALS model chain (default claude-sonnet-4-6)

launchClaudePty spawned the interactive `claude` TUI with no --model flag, so
the child inherited the operator's ~/.claude/settings.json model. On a
slow-thinking model that meant 5+ min of extended thinking on empty plan-mode
context, timing out the plan-mode smoke tests regardless of contention. Pin the
model via opts.model ?? EVALS_MODEL ?? 'claude-sonnet-4-6' — byte-identical to
session-runner.ts:144, so PTY and `claude -p` evals always agree.

Pushed before extraArgs (last flag wins, so a per-test --model still overrides).
Placement leaves the spawn region byte-stable for a clean merge with the
in-flight hermetic-env branch. Plumbed model through the three plan-skill
wrappers. Static-grep tripwires guard the pin, its fallback chain, the
before-extraArgs ordering, and all three wrapper forwards.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

test/helpers/claude-pty-runner.ts

@@ -70,6 +70,15 @@ export interface ClaudePtyOptions {
   permissionMode?: 'plan' | 'default' | 'acceptEdits' | 'bypassPermissions' | 'auto' | 'dontAsk' | null;
   /** Extra args after the permission-mode flag. */
   extraArgs?: string[];
+  /**
+   * Model for the spawned interactive `claude`. Without an explicit --model the
+   * child inherits the operator's ~/.claude/settings.json model (e.g.
+   * claude-fable-5[1m]), which can spend 5+ min in extended thinking on an empty
+   * plan-mode context and blow every smoke budget. Resolution mirrors
+   * session-runner.ts:144 exactly: opts.model ?? EVALS_MODEL ?? 'claude-sonnet-4-6'.
+   * Pushed BEFORE extraArgs so a test-supplied --model still wins (last flag wins).
+   */
+  model?: string;
   /** Terminal size. Default 120x40. Plan-mode UI lays out cleanly at this size. */
   cols?: number;
   rows?: number;
@@ -1137,9 +1146,15 @@ export async function launchClaudePty(
   let exited = false;
   let exitCodeCaptured: number | null = null;
 
+  const args: string[] = [];
+  // Pin the model so smokes don't inherit the operator's settings.json model
+  // (see ClaudePtyOptions.model). Chain mirrors session-runner.ts:144 so PTY and
+  // `claude -p` evals always agree. Pushed before extraArgs => a test-supplied
+  // --model wins (last flag wins).
+  const model = opts.model ?? process.env.EVALS_MODEL ?? 'claude-sonnet-4-6';
+  args.push('--model', model);
   // Permission mode: 'plan' default, null => omit flag entirely.
   const permissionMode = opts.permissionMode === undefined ? 'plan' : opts.permissionMode;
-  const args: string[] = [];
   if (permissionMode !== null) {
     args.push('--permission-mode', permissionMode);
   }
@@ -1480,6 +1495,9 @@ export async function runPlanSkillObservation(opts: {
    * Step 0 reads the prior conversation context so it sees the draft.
    */
   initialPlanContent?: string;
+  /** Override the spawned model. Defaults via launchClaudePty's chain
+   *  (opts.model ?? EVALS_MODEL ?? 'claude-sonnet-4-6'). */
+  model?: string;
 }): Promise<PlanSkillObservation> {
   const startedAt = Date.now();
   const session = await launchClaudePty({
@@ -1488,6 +1506,7 @@ export async function runPlanSkillObservation(opts: {
     timeoutMs: (opts.timeoutMs ?? 180_000) + 30_000,
     extraArgs: opts.extraArgs,
     env: opts.env,
+    model: opts.model,
   });
 
   try {
@@ -1744,6 +1763,8 @@ export async function runPlanSkillCounting(opts: {
   timeoutMs?: number;
   /** Extra env merged into the spawned `claude` process. */
   env?: Record<string, string>;
+  /** Override the spawned model. Defaults via launchClaudePty's chain. */
+  model?: string;
 }): Promise<PlanSkillCountObservation> {
   const startedAt = Date.now();
   const defaultPick = opts.defaultPick ?? 1;
@@ -1754,6 +1775,7 @@ export async function runPlanSkillCounting(opts: {
     cwd: opts.cwd,
     timeoutMs: timeoutMs + 60_000,
     env: opts.env,
+    model: opts.model,
   });
 
   const fingerprints: AskUserQuestionFingerprint[] = [];
@@ -1975,6 +1997,8 @@ export async function runPlanSkillFloorCheck(opts: {
   timeoutMs?: number;
   /** Extra env merged into the spawned `claude` process. */
   env?: Record<string, string>;
+  /** Override the spawned model. Defaults via launchClaudePty's chain. */
+  model?: string;
 }): Promise<PlanSkillFloorObservation> {
   const startedAt = Date.now();
   const timeoutMs = opts.timeoutMs ?? 600_000;
@@ -1984,6 +2008,7 @@ export async function runPlanSkillFloorCheck(opts: {
     cwd: opts.cwd,
     timeoutMs: timeoutMs + 60_000,
     env: opts.env,
+    model: opts.model,
   });
 
   try {

test/helpers/claude-pty-runner.unit.test.ts

@@ -23,6 +23,7 @@
  */
 
 import { describe, test, expect } from 'bun:test';
+import { readFileSync } from 'node:fs';
 import {
   isPermissionDialogVisible,
   isNumberedOptionListVisible,
@@ -552,6 +553,45 @@ describe('runPlanSkillObservation env passthrough surface', () => {
   });
 });
 
+describe('launchClaudePty model pin (static tripwire)', () => {
+  // Why static-grep, not a behavioral assert: the spawn fires immediately
+  // inside launchClaudePty, so asserting the built args array would require
+  // extracting an arg-builder seam — which rewrites the exact region kyoto-v5's
+  // hermetic --strict-mcp-config insertion edits, reintroducing a merge
+  // conflict the placement deliberately avoids. The end-to-end behavioral proof
+  // is the live PTY smoke (skill-e2e-plan-*-plan-mode.test.ts) running under the
+  // pinned model. These grep-level guards stop a refactor from silently
+  // dropping the pin or reordering it past extraArgs.
+  const src = readFileSync(new URL('./claude-pty-runner.ts', import.meta.url), 'utf-8');
+
+  test('ClaudePtyOptions exposes model?: string', () => {
+    const opts: ClaudePtyOptions = { model: 'claude-sonnet-4-6' };
+    expect(opts.model).toBe('claude-sonnet-4-6');
+  });
+
+  test('spawn args push --model from the EVALS_MODEL fallback chain', () => {
+    expect(src).toContain("args.push('--model', model)");
+    // opts.model -> EVALS_MODEL -> 'claude-sonnet-4-6' (mirrors session-runner.ts:144)
+    expect(src).toMatch(
+      /opts\.model\s*\?\?\s*process\.env\.EVALS_MODEL\s*\?\?\s*'claude-sonnet-4-6'/,
+    );
+  });
+
+  test('--model is pushed BEFORE extraArgs so a per-test --model override wins', () => {
+    const modelPush = src.indexOf("args.push('--model', model)");
+    const extraArgsPush = src.indexOf('if (opts.extraArgs) args.push(...opts.extraArgs)');
+    expect(modelPush).toBeGreaterThan(-1);
+    expect(extraArgsPush).toBeGreaterThan(-1);
+    expect(modelPush).toBeLessThan(extraArgsPush);
+  });
+
+  test('all three plan-skill wrappers forward model to launchClaudePty', () => {
+    // Count must match the number of wrappers (observation, counting, floor).
+    const forwards = src.match(/^\s*model: opts\.model,$/gm) ?? [];
+    expect(forwards.length).toBe(3);
+  });
+});
+
 // ────────────────────────────────────────────────────────────────────────────
 // Per-finding count primitives — Section 3 unit tests #1–#5, #7, #12.
 // ────────────────────────────────────────────────────────────────────────────