feat(dispatch): add QA Lead director for hands-on product proof

docs/ARCHITECTURE.md

@@ -278,7 +278,7 @@ Enforcement is runtime code at the existing tool-mount point, not prompt wording
 
 #### Closed director fleet (`src/agent/directors/`)
 
-Every shipped specialist is a **director package** — a prompt-first `DirectorPackage` (system prompt, tool envelope, spawn rights, nudge budget, report contract, `modelRole`, fleet authority `tier`) registered in a **closed** set of 10 ids. There is no catch-all worker: `spawn_agent` without `agent` or non-general `intent`, and `spawn_agent(intent="general")`, fail closed so the primary reclassifies. Nested directors with a spawn allowlist reject off-list children at `spawn_agent` dispatch time (not prompt-only). dispatch is the primary session identity: `spawn_agent(agent="dispatch")` is refused, and `directorProfiles()` omits it from the spawn catalog.
+Every shipped specialist is a **director package** — a prompt-first `DirectorPackage` (system prompt, tool envelope, spawn rights, nudge budget, report contract, `modelRole`, fleet authority `tier`) registered in a **closed** set of 11 ids. There is no catch-all worker: `spawn_agent` without `agent` or non-general `intent`, and `spawn_agent(intent="general")`, fail closed so the primary reclassifies. Nested directors with a spawn allowlist reject off-list children at `spawn_agent` dispatch time (not prompt-only). dispatch is the primary session identity: `spawn_agent(agent="dispatch")` is refused, and `directorProfiles()` omits it from the spawn catalog.
 
 **Primary**
 
@@ -288,17 +288,18 @@ Every shipped specialist is a **director package** — a prompt-first `DirectorP
 
 **Specialists**
 
-| Director    | Owns                                                                 | Does not own           |
-| ----------- | -------------------------------------------------------------------- | ---------------------- |
-| explorer    | Read-only codebase mapping                                           | Product edits          |
-| planner     | PRD.md, SOLUTION_SCOPE.md, BUILD_PLAN.md authoring                   | Code                   |
-| coder       | Minimal safe diffs, root-cause fixes, tests                          | Pure docs, pure review |
-| reviewer    | Evidence-based defect and quality review with temp-test verification | Fixing product code    |
-| designer    | DESIGN.md, design laws, tokens, interface polish                     | Non-UI product code    |
-| artist      | SVGs, diagrams, generative graphic prompts                           | Product code           |
-| warden      | Trust review of permission, provider-auth, and plugin-loader diffs   | Fixes, general review  |
-| shakespeare | Docs maintenance (PRODUCT / ARCHITECTURE / IMPLEMENTATION)           | Product code           |
-| prober      | Measure-only latency and behavior probe per family/model             | Fixes, product edits   |
+| Director    | Owns                                                                 | Does not own                       |
+| ----------- | -------------------------------------------------------------------- | ---------------------------------- |
+| explorer    | Read-only codebase mapping                                           | Product edits                      |
+| planner     | PRD.md, SOLUTION_SCOPE.md, BUILD_PLAN.md authoring                   | Code                               |
+| coder       | Minimal safe diffs, root-cause fixes, tests                          | Pure docs, pure review             |
+| reviewer    | Evidence-based defect and quality review with temp-test verification | Fixing product code                |
+| designer    | DESIGN.md, design laws, tokens, interface polish                     | Non-UI product code                |
+| artist      | SVGs, diagrams, generative graphic prompts                           | Product code                       |
+| warden      | Trust review of permission, provider-auth, and plugin-loader diffs   | Fixes, general review              |
+| shakespeare | Docs maintenance (PRODUCT / ARCHITECTURE / IMPLEMENTATION)           | Product code                       |
+| prober      | Measure-only latency and behavior probe per family/model             | Fixes, product edits               |
+| qa-lead     | QA Lead: hands-on CLI, e2e, occupancy, capability proof              | Unit tests, latency, product fixes |
 
 **Intent → director** (`spawn_agent(intent=…)` when `agent` is omitted). implement/review (and their default directors) fail closed without non-empty `success_criteria`.
 

docs/PRODUCT.md

@@ -155,12 +155,12 @@ Capabilities beyond the core toolset are opt-in plugins, enabled per workspace t
 
 ## Multi-agent (fleet agents)
 
-The primary session is always **orchestrator** (single-agent mode is gone). Its director is **dispatch**: classify work, DIY tiny/single-file/one-route product edits, dispatch a **closed fleet of 10 directors** for substantial work, track the fleet, and synthesize. Product mutation tools (`write_file` / `edit_file` / `delete_file`) are mounted on the primary (CORE / `DISPATCH_TOOLS`) — path tools are the DIY surface; spawn remains the default for substantial, multi-file, parallel, or specialist work. Shell file-writes stay denied. MCP tools are not re-filtered by a product-write deny list (that list is gone). There is no static per-package write-path declaration (CL-6952 removed it — no shipped director ever set one). A concurrent dispatch landing on the same working directory as another still-running lane is recorded as a `conflict` intervention, not blocked. Operator slash recipes (`/implement`, `/plan`, `/refactor`, `/review`, `/pull-request`, `/issue`, `/docs`, `/interview`) tell dispatch which directors to spawn for substantial work; tiny/bounded edits may run on the primary.
+The primary session is always **orchestrator** (single-agent mode is gone). Its director is **dispatch**: classify work, DIY tiny/single-file/one-route product edits, dispatch a **closed fleet of 11 directors** for substantial work, track the fleet, and synthesize. Product mutation tools (`write_file` / `edit_file` / `delete_file`) are mounted on the primary (CORE / `DISPATCH_TOOLS`) — path tools are the DIY surface; spawn remains the default for substantial, multi-file, parallel, or specialist work. Shell file-writes stay denied. MCP tools are not re-filtered by a product-write deny list (that list is gone). There is no static per-package write-path declaration (CL-6952 removed it — no shipped director ever set one). A concurrent dispatch landing on the same working directory as another still-running lane is recorded as a `conflict` intervention, not blocked. Operator slash recipes (`/implement`, `/plan`, `/refactor`, `/review`, `/pull-request`, `/issue`, `/docs`, `/interview`) tell dispatch which directors to spawn for substantial work; tiny/bounded edits may run on the primary.
 
-| Role       | Directors                                                                         |
-| ---------- | --------------------------------------------------------------------------------- |
-| Primary    | dispatch                                                                          |
-| Specialist | explorer, planner, coder, reviewer, designer, artist, warden, shakespeare, prober |
+| Role       | Directors                                                                                  |
+| ---------- | ------------------------------------------------------------------------------------------ |
+| Primary    | dispatch                                                                                   |
+| Specialist | explorer, planner, coder, reviewer, designer, artist, warden, shakespeare, prober, qa-lead |
 
 There is **no catch-all worker**. `spawn_agent` requires `agent=…` or a non-general `intent` (implement→coder, explore→explorer, plan→planner, review→reviewer); bare dispatch and `intent=general` are refused. Named `spawn_agent(agent=…)` selects a director package without requiring a plugin profile, except `dispatch` which is the primary session identity and is refused as a spawned worker. Nested spawn is runtime-enforced: only dispatch (full fleet allowlist) may spawn; all other workers, have no fleet tools. Primary omits an allowlist so plugin profiles remain reachable from the main session.
 

scripts/ci-timings.json

@@ -451,7 +451,7 @@
     "src/agent/directors/prober/package.test.ts": 1,
     "src/agent/directors/rand/package.test.ts": 1,
     "src/agent/directors/shakespeare/package.test.ts": 1,
-    "src/agent/directors/tester/package.test.ts": 1,
+    "src/agent/directors/qa-lead/package.test.ts": 1,
     "src/agent/directors/warden/package.test.ts": 1,
     "src/agent/grok-residual.test.ts": 1,
     "src/agent/tool-classification.test.ts": 1,

src/agent/directors/dispatch/package.ts

@@ -16,6 +16,7 @@ You are Dispatch, the coordinator for Corbits Code. Specialists own substantive
 - Security auditing, trust boundaries, permissions, or secret guard review: spawn warden (permission and trust review).
 - Product, architecture, or implementation documentation: spawn shakespeare (PRODUCT, ARCHITECTURE, IMPLEMENTATION docs).
 - Model distribution benchmarks, latency probing, or prompt evaluation: spawn prober (latency and behavior distributions).
+- Hands-on product exercise, e2e, occupancy, or actually using the CLI: spawn qa-lead (behavior proof, pass/fail with commands). Distinct from coder unit tests and prober measurement.
 
 # Delegation boundary
 - Delegate by default. File count does not determine complexity: a single-file bug fix or behavior change still belongs to coder.
@@ -75,6 +76,7 @@ export const dispatchPackage: DirectorPackage = {
       "warden",
       "shakespeare",
       "prober",
+      "qa-lead",
     ],
   },
   modelRole: "orchestrator",

src/agent/directors/qa-lead/package.ts

@@ -0,0 +1,59 @@
+import type { DirectorPackage } from "../types.js";
+import { REVIEW_TOOLS } from "../tool-sets.js";
+
+/**
+ * QA Lead worker (CL-9903).
+ * Hands-on product exercise — actually run the CLI / e2e / occupancy /
+ * capability path as behavior proof (pass/fail with commands); never author
+ * unit tests, never measure family/model latency, never fix product code.
+ */
+export const qaLeadPackage: DirectorPackage = {
+  id: "qa-lead",
+  primaryIntent:
+    "Hands-on product exercise: actually run CLI/e2e/occupancy/capability as proof (pass/fail with commands); never author unit tests, never measure latency, never fix product code",
+  outOfLane: [
+    "authoring unit tests (coder)",
+    "measuring family/model latency (prober)",
+    "fixing product code",
+    "fleet orchestration or spawning",
+  ],
+  description:
+    "QA Lead — hands-on product exercise: CLI/e2e/occupancy/capability proof",
+  systemPrompt: `You are QA Lead (\`qa-lead\`), a specialist in Corbits Code.
+
+PRIMARY INTENT: hands-on product exercise. Actually run the product as an operator would and report behavior as proof — pass/fail with exact commands. Never author unit tests. Never measure family/model latency. Never fix product code. Never spawn.
+
+You are the hands-on lane — not Coder (unit tests with product diffs), not Prober (family/model latency matrices), not Reviewer, not an orchestrator, not a product fixer. Do not spawn specialists. Do not edit product code to make a failing exercise pass; a test that moves the target is not an exercise.
+
+BLINDERS ON: exercise what the brief's success_criteria ask for, on the product below. Do not wander into unit-test authorship, latency matrices, or product fixes.
+
+# What to run
+
+- The operator CLI: \`corbits\` and \`corbits exec\` against fixture copies or the worktree the brief names.
+- Integration scenarios: \`bun test ./e2e\` — production agent loop, compaction occupancy, mailbox, permission, spawn lanes.
+- Capability runs as behavior: \`bun run eval:capability\` (\`scripts/eval-capability.ts\` over \`evals/capability\`) — pass/fail of the product path, not a latency matrix.
+
+# How to judge
+
+- Each success_criteria item is pass, fail, or blocked, with the exact command, exit status, and relevant output.
+- Compaction occupancy: run the e2e compaction suite (\`e2e/compaction-*.test.ts\` and related occupancy coverage) and report whether occupancy, mailbox mail, and compact-then-continue actually behave.
+- Do not author \`src/**/*.test.ts\` unit tests — that is Coder's lane. Temporary repro files under \`tmp/\` are allowed only when the brief needs a scripted operator session, then clean them up.
+- Do not slice by family/model latency (TTFT, tool-only streaks, salvage/nudge counts) — that is Prober's lane. A capability run here is a behavior verdict, not a distribution.
+
+# Findings route to follow-ups, never silent product edits
+
+- Report commands, exit codes, and failing output so Coder can reproduce.
+- Product-looking conclusions go to Blockers as follow-up tickets — do not patch src/ here.
+
+# Report
+
+When done, stop tooling and reply with ONLY the Corbits report envelope — the shared scaffold owns its shape (Summary / Findings / Blockers / Paths, in that order), so this package does not re-specify it. Findings for this lane: pass/fail/blocked per success_criteria item, exact commands and exit statuses, occupancy/e2e/CLI evidence.
+
+DONE GATE: stop when the brief's exercise ask is answered with evidence OR explicitly blocked under Blockers. Do not expand into unit tests, latency matrices, product fixes, or orchestration.
+
+OUT OF LANE: authoring unit tests (route to coder), measuring family/model latency (route to prober), fixing product code, fleet orchestration, spawning.`,
+  tools: { allow: REVIEW_TOOLS },
+  spawn: { maySpawn: false },
+  tier: "leaf",
+  modelRole: "test",
+};

src/agent/directors/registry.test.ts

@@ -13,9 +13,9 @@ import {
 } from "./registry.js";
 
 describe("director registry", () => {
-  test("closed set has exactly 10 directors", () => {
-    expect(DIRECTOR_IDS).toHaveLength(10);
-    expect(listDirectors()).toHaveLength(10);
+  test("closed set has exactly 11 directors", () => {
+    expect(DIRECTOR_IDS).toHaveLength(11);
+    expect(listDirectors()).toHaveLength(11);
     for (const id of DIRECTOR_IDS) {
       expect(DIRECTOR_REGISTRY[id].id).toBe(id);
     }
@@ -116,7 +116,7 @@ describe("director registry", () => {
 
   test("directorProfiles is the spawn catalog (closed set minus dispatch)", () => {
     const profiles = directorProfiles();
-    expect(profiles).toHaveLength(9);
+    expect(profiles).toHaveLength(10);
     expect(profiles.map((p) => p.id)).not.toContain("dispatch");
   });
 
@@ -157,7 +157,7 @@ describe("director registry", () => {
     expect(s.tools?.allow).toContain("write_file");
     expect(s.tools?.allow).toContain("edit_file");
     expect(s.tools?.allow).toContain("delete_file");
-    expect(s.spawn.allowlist).toHaveLength(9);
+    expect(s.spawn.allowlist).toHaveLength(10);
   });
 
   test("tier agrees with spawn.maySpawn for every director", () => {
@@ -182,6 +182,36 @@ describe("director registry", () => {
     expect(tierForDirectorId("prober")).toBe("leaf");
   });
 
+  test("qa-lead is a hands-on leaf, not prober, with no spawn", () => {
+    const r = resolveDirector({ agentId: "qa-lead" });
+    expect(r.ok).toBe(true);
+    if (r.ok) {
+      expect(r.package.id).toBe("qa-lead");
+      expect(r.package.tier).toBe("leaf");
+      expect(r.package.spawn.maySpawn).toBe(false);
+      expect(r.package.modelRole).toBe("test");
+      expect(r.package.tools?.allow).toContain("write_file");
+      expect(r.package.description).toMatch(/QA Lead/);
+      expect(r.package.systemPrompt).toMatch(/QA Lead/);
+      expect(r.package.systemPrompt).toMatch(/hands-on/i);
+      expect(r.package.systemPrompt).toMatch(/corbits exec/i);
+      expect(r.package.systemPrompt).toMatch(/bun test \.\/e2e/);
+      expect(r.package.systemPrompt).toMatch(/eval:capability/);
+      expect(r.package.systemPrompt).toMatch(/occupancy/i);
+      expect(r.package.systemPrompt).toMatch(/never author unit tests/i);
+      expect(r.package.systemPrompt).toMatch(
+        /never measure family\/model latency/i,
+      );
+      expect(r.package.systemPrompt).toMatch(/never fix product code/i);
+      expect(r.package).not.toBe(DIRECTOR_REGISTRY.prober);
+    }
+    expect(isDirectorId("qa-lead")).toBe(true);
+    expect(isDirectorId("tester")).toBe(false);
+    expect(tierForDirectorId("qa-lead")).toBe("leaf");
+    expect(DIRECTOR_REGISTRY.dispatch.spawn.allowlist).toContain("qa-lead");
+    expect(DIRECTOR_REGISTRY.dispatch.spawn.allowlist).not.toContain("tester");
+  });
+
   test("dispatch card has no parallelization cap; duplicate is the same live job", () => {
     const card = DIRECTOR_REGISTRY.dispatch.systemPrompt;
     expect(card).toContain("no parallelization cap");

src/agent/directors/registry.ts

@@ -6,6 +6,7 @@ import { dispatchPackage } from "./dispatch/package.js";
 import { explorerPackage } from "./explorer/package.js";
 import { plannerPackage } from "./planner/package.js";
 import { proberPackage } from "./prober/package.js";
+import { qaLeadPackage } from "./qa-lead/package.js";
 import { reviewerPackage } from "./reviewer/package.js";
 import { shakespearePackage } from "./shakespeare/package.js";
 import { wardenPackage } from "./warden/package.js";
@@ -46,6 +47,7 @@ export const DIRECTOR_REGISTRY: Readonly<Record<DirectorId, DirectorPackage>> =
     warden: wardenPackage,
     shakespeare: shakespearePackage,
     prober: proberPackage,
+    "qa-lead": qaLeadPackage,
   };
 
 export function isDirectorId(value: unknown): value is DirectorId {

src/agent/directors/types.ts

@@ -14,6 +14,7 @@ export const DIRECTOR_IDS = [
   "warden",
   "shakespeare",
   "prober",
+  "qa-lead",
 ] as const;
 
 export type DirectorId = (typeof DIRECTOR_IDS)[number];

src/agent/prompt-sizes.test.ts

@@ -44,6 +44,7 @@ const PROMPT_SIZE_BASELINE: Record<
   warden: { chars: 4113, bytes: 4127 },
   shakespeare: { chars: 5993, bytes: 6015 },
   prober: { chars: 5428, bytes: 5454 },
+  "qa-lead": { chars: 5226, bytes: 5246 },
 };
 
 /**