feat(gsd): extend flat-rate provider detection to custom/externalCli providers

The 3-entry hard-coded FLAT_RATE_PROVIDERS set in auto-model-selection.ts
treated only github-copilot/copilot/claude-code as flat-rate, so dynamic
routing would happily downgrade units on user-registered subscription
proxies and any externalCli CLI wrapper — quality loss with no cost
benefit for users whose provider charges a flat rate per request.

Make isFlatRateProvider extensible by composing three signals:

  1. Built-in list (unchanged, wins first for regression safety).
  2. externalCli auto-detection via ctx.modelRegistry.getProviderAuthMode()
     — any CLI wrapper around the user's subscription is inherently
     flat-rate.
  3. User-declared `flat_rate_providers` preference for private
     subscription-backed proxies, enterprise-gated deployments, and custom
     CLI wrappers the built-in list doesn't know about.

Add a buildFlatRateContext() helper so every call site constructs the
context the same way and degrades gracefully when ctx/prefs/registry are
unavailable (never breaks flat-rate detection).

Thread the context through:

- resolvePreferredModelConfig (routing synthesis guard)
- selectAndApplyModel primary-model and fallback provider checks
- auto-start.ts dynamic-routing banner so the startup message matches
  dispatch-time reality

Preferences:
- Add `flat_rate_providers?: string[]` to GSDPreferences and
  KNOWN_PREFERENCE_KEYS in preferences-types.ts.
- Add a string-array validator in preferences-validation.ts that trims
  whitespace and drops empty entries.

Tests:
- Extend flat-rate-routing-guard.test.ts with 13 new cases covering
  externalCli auto-detection, userFlatRate preference matching
  (case-insensitive), combined signals, buildFlatRateContext() behavior
  (including registry-lookup-throws and non-canonical auth-mode
  responses), plus regression cases for the built-in list.
- Add 5 validator cases in preferences.test.ts for the new
  flat_rate_providers field (string-array accepted, whitespace trimmed,
  non-array rejected, non-string elements rejected, known-key warning
  check).

src/resources/extensions/gsd/auto-model-selection.ts

@@ -29,6 +29,10 @@ export function resolvePreferredModelConfig(
   /** When false, only return explicit per-phase model configs — do not
    *  synthesize a routing ceiling from dynamic_routing.tier_models (#3962). */
   isAutoMode = true,
+  /** Optional flat-rate context for the start model's provider.  Used to
+   *  extend flat-rate detection beyond the built-in list (user
+   *  `flat_rate_providers` preference + externalCli auto-detection). */
+  flatRateCtx?: FlatRateContext,
 ) {
   const explicitConfig = resolveModelWithFallbacksForUnit(unitType);
   if (explicitConfig) return explicitConfig;
@@ -41,7 +45,7 @@ export function resolvePreferredModelConfig(
   if (!routingConfig.enabled || !routingConfig.tier_models) return undefined;
 
   // Don't synthesize a routing config for flat-rate providers (#3453).
-  if (autoModeStartModel && isFlatRateProvider(autoModeStartModel.provider)) return undefined;
+  if (autoModeStartModel && isFlatRateProvider(autoModeStartModel.provider, flatRateCtx)) return undefined;
 
   const ceilingModel = routingConfig.tier_models.heavy
     ?? (autoModeStartModel ? `${autoModeStartModel.provider}/${autoModeStartModel.id}` : undefined);
@@ -79,9 +83,17 @@ export async function selectAndApplyModel(
   const effectiveSessionModelOverride = sessionModelOverride === undefined
     ? getSessionModelOverride(ctx.sessionManager.getSessionId())
     : (sessionModelOverride ?? undefined);
+  // Build a flat-rate context for the start model's provider up front so
+  // routing synthesis and the dispatch-time guard see the same signals
+  // (built-in list + user `flat_rate_providers` preference + externalCli
+  // auto-detection).  The dispatch-time primary-model check below builds
+  // its own per-provider context when it has a resolved primary model.
+  const startModelFlatRateCtx = autoModeStartModel
+    ? buildFlatRateContext(autoModeStartModel.provider, ctx, prefs)
+    : undefined;
   const modelConfig = effectiveSessionModelOverride
     ? undefined
-    : resolvePreferredModelConfig(unitType, autoModeStartModel, isAutoMode);
+    : resolvePreferredModelConfig(unitType, autoModeStartModel, isAutoMode, startModelFlatRateCtx);
   let routing: { tier: string; modelDowngraded: boolean } | null = null;
   let appliedModel: Model<Api> | null = null;
 
@@ -107,12 +119,16 @@ export async function selectAndApplyModel(
     if (routingConfig.enabled) {
       const primaryModel = resolveModelId(modelConfig.primary, availableModels, ctx.model?.provider);
       if (primaryModel) {
-        if (isFlatRateProvider(primaryModel.provider)) {
+        const primaryFlatRateCtx = buildFlatRateContext(primaryModel.provider, ctx, prefs);
+        if (isFlatRateProvider(primaryModel.provider, primaryFlatRateCtx)) {
           routingConfig.enabled = false;
         }
       } else if (
-        (autoModeStartModel && isFlatRateProvider(autoModeStartModel.provider))
-        || (ctx.model?.provider && isFlatRateProvider(ctx.model.provider))
+        (autoModeStartModel && isFlatRateProvider(autoModeStartModel.provider, startModelFlatRateCtx))
+        || (ctx.model?.provider && isFlatRateProvider(
+          ctx.model.provider,
+          buildFlatRateContext(ctx.model.provider, ctx, prefs),
+        ))
       ) {
         // Primary model unresolvable but provider signals indicate flat-rate —
         // disable routing to prevent quality degradation.
@@ -416,8 +432,63 @@ export function resolveModelId<T extends { id: string; provider: string }>(
  * Uses case-insensitive matching with alias support to prevent fail-open on
  * provider naming variations (e.g. "copilot" vs "github-copilot").
  */
-const FLAT_RATE_PROVIDERS = new Set(["github-copilot", "copilot", "claude-code"]);
+const BUILTIN_FLAT_RATE = new Set(["github-copilot", "copilot", "claude-code"]);
 
-export function isFlatRateProvider(provider: string): boolean {
-  return FLAT_RATE_PROVIDERS.has(provider.toLowerCase());
+/**
+ * Optional context that lets callers extend flat-rate detection beyond the
+ * hard-coded built-in list.  Either signal on its own is enough to classify
+ * a provider as flat-rate.
+ */
+export interface FlatRateContext {
+  /**
+   * Auth mode for the specific provider being checked, as returned by
+   * `ctx.modelRegistry.getProviderAuthMode(provider)`.  Any provider that
+   * wraps a local CLI (externalCli) is, by definition, a flat-rate
+   * subscription wrapper — every request costs the same regardless of
+   * model, so dynamic routing only degrades quality.
+   */
+  authMode?: "apiKey" | "oauth" | "externalCli" | "none";
+  /**
+   * Case-insensitive list of extra provider IDs the user has declared as
+   * flat-rate via `preferences.flat_rate_providers`.  Used for private
+   * subscription-backed proxies and enterprise-gated deployments that the
+   * built-in list doesn't know about.
+   */
+  userFlatRate?: readonly string[];
+}
+
+export function isFlatRateProvider(provider: string, opts?: FlatRateContext): boolean {
+  const p = provider.toLowerCase();
+  if (BUILTIN_FLAT_RATE.has(p)) return true;
+  if (opts?.userFlatRate?.some(id => id.toLowerCase() === p)) return true;
+  if (opts?.authMode === "externalCli") return true;
+  return false;
+}
+
+/**
+ * Build a FlatRateContext for a given provider from live runtime state.
+ * Safe to call when ctx or prefs are undefined — missing pieces are
+ * treated as "no signal".
+ */
+export function buildFlatRateContext(
+  provider: string,
+  ctx?: { modelRegistry?: { getProviderAuthMode?: (p: string) => string } },
+  prefs?: { flat_rate_providers?: readonly string[] },
+): FlatRateContext {
+  let authMode: FlatRateContext["authMode"];
+  const getAuthMode = ctx?.modelRegistry?.getProviderAuthMode;
+  if (typeof getAuthMode === "function") {
+    try {
+      const mode = getAuthMode(provider);
+      if (mode === "apiKey" || mode === "oauth" || mode === "externalCli" || mode === "none") {
+        authMode = mode;
+      }
+    } catch {
+      // Registry lookup failure must never break flat-rate detection.
+    }
+  }
+  return {
+    authMode,
+    userFlatRate: prefs?.flat_rate_providers,
+  };
 }

src/resources/extensions/gsd/auto-start.ts

@@ -825,12 +825,19 @@ export async function bootstrapAutoSession(
       ? `${s.autoModeStartModel.provider}/${s.autoModeStartModel.id}`
       : ctx.model ? `${ctx.model.provider}/${ctx.model.id}` : "default";
 
-    // Flat-rate providers (e.g. GitHub Copilot, claude-code) suppress routing
-    // at dispatch time (#3453) — reflect that in the banner.
-    const { isFlatRateProvider } = await import("./auto-model-selection.js");
+    // Flat-rate providers (e.g. GitHub Copilot, claude-code, user-declared
+    // subscription proxies, externalCli CLIs) suppress routing at dispatch
+    // time (#3453) — reflect that in the banner.  Thread the same
+    // FlatRateContext used by selectAndApplyModel so user-declared
+    // flat-rate providers and externalCli auto-detection are respected.
+    const { isFlatRateProvider, buildFlatRateContext } = await import("./auto-model-selection.js");
+    const bannerPrefs = loadEffectiveGSDPreferences()?.preferences;
     const effectiveProvider = s.autoModeStartModel?.provider ?? ctx.model?.provider;
     const effectivelyEnabled = routingConfig.enabled
-      && !(effectiveProvider && isFlatRateProvider(effectiveProvider));
+      && !(effectiveProvider && isFlatRateProvider(
+        effectiveProvider,
+        buildFlatRateContext(effectiveProvider, ctx, bannerPrefs),
+      ));
 
     // The actual ceiling may come from tier_models.heavy, not the start model.
     const effectiveCeiling = (routingConfig.enabled && routingConfig.tier_models?.heavy)

src/resources/extensions/gsd/preferences-types.ts

@@ -113,6 +113,7 @@ export const KNOWN_PREFERENCE_KEYS = new Set<string>([
   "discuss_preparation",
   "discuss_web_research",
   "discuss_depth",
+  "flat_rate_providers",
 ]);
 
 /** Canonical list of all dispatch unit types. */
@@ -359,6 +360,17 @@ export interface GSDPreferences {
    * Default: "standard".
    */
   discuss_depth?: "quick" | "standard" | "thorough";
+  /**
+   * Extra provider IDs to treat as flat-rate (no cost benefit from dynamic
+   * routing).  Dynamic routing is suppressed for any provider listed here,
+   * in addition to the built-in list (github-copilot, copilot, claude-code)
+   * and any provider auto-detected via `authMode: "externalCli"`.
+   *
+   * Intended for private subscription-backed proxies, enterprise-gated
+   * deployments, and custom CLI wrappers where every request costs the
+   * same regardless of model.  Case-insensitive.
+   */
+  flat_rate_providers?: string[];
 }
 
 export interface LoadedGSDPreferences {

src/resources/extensions/gsd/preferences-validation.ts

@@ -180,6 +180,29 @@ export function validatePreferences(preferences: GSDPreferences): {
     }
   }
 
+  // ─── Flat-rate Providers ────────────────────────────────────────────
+  // User-declared flat-rate providers for dynamic routing suppression.
+  // Built-in providers (github-copilot, copilot, claude-code) and any
+  // externalCli provider are already auto-detected; this list layers on
+  // top for private subscription proxies and custom CLI wrappers.
+  if (preferences.flat_rate_providers !== undefined) {
+    if (Array.isArray(preferences.flat_rate_providers)) {
+      const allStrings = preferences.flat_rate_providers.every(
+        (item: unknown) => typeof item === "string",
+      );
+      if (allStrings) {
+        // Strip empty/whitespace-only entries to avoid false matches.
+        validated.flat_rate_providers = preferences.flat_rate_providers
+          .map((s: string) => s.trim())
+          .filter((s: string) => s.length > 0);
+      } else {
+        errors.push("flat_rate_providers must be an array of strings");
+      }
+    } else {
+      errors.push("flat_rate_providers must be an array of strings");
+    }
+  }
+
   // ─── Phase Skip Preferences ─────────────────────────────────────────
   if (preferences.phases !== undefined) {
     if (typeof preferences.phases === "object" && preferences.phases !== null) {

src/resources/extensions/gsd/tests/flat-rate-routing-guard.test.ts

@@ -6,7 +6,7 @@
 
 import { describe, test } from "node:test";
 import assert from "node:assert/strict";
-import { isFlatRateProvider, resolvePreferredModelConfig } from "../auto-model-selection.ts";
+import { buildFlatRateContext, isFlatRateProvider, resolvePreferredModelConfig } from "../auto-model-selection.ts";
 
 describe("flat-rate provider routing guard (#3453)", () => {
 
@@ -48,3 +48,139 @@ describe("flat-rate provider routing guard (#3453)", () => {
     assert.equal(result, undefined, "Should not create routing config for copilot");
   });
 });
+
+describe("flat-rate provider extensibility (any/all/custom)", () => {
+  test("regression: built-in providers still flat-rate with no context", () => {
+    assert.equal(isFlatRateProvider("github-copilot"), true);
+    assert.equal(isFlatRateProvider("copilot"), true);
+    assert.equal(isFlatRateProvider("claude-code"), true);
+  });
+
+  test("regression: non-flat-rate API providers return false with no context", () => {
+    assert.equal(isFlatRateProvider("anthropic"), false);
+    assert.equal(isFlatRateProvider("openai"), false);
+    assert.equal(isFlatRateProvider("google-vertex"), false);
+  });
+
+  test("auto-detection: externalCli auth mode marks provider flat-rate", () => {
+    // Any provider registered with authMode: "externalCli" is a local
+    // CLI wrapper around the user's subscription — every request costs
+    // the same regardless of model, so dynamic routing provides no benefit.
+    assert.equal(
+      isFlatRateProvider("my-private-cli", { authMode: "externalCli" }),
+      true,
+    );
+  });
+
+  test("auto-detection: non-externalCli auth modes do not mark provider flat-rate", () => {
+    assert.equal(
+      isFlatRateProvider("my-http-proxy", { authMode: "apiKey" }),
+      false,
+    );
+    assert.equal(
+      isFlatRateProvider("my-http-proxy", { authMode: "oauth" }),
+      false,
+    );
+    assert.equal(
+      isFlatRateProvider("my-http-proxy", { authMode: "none" }),
+      false,
+    );
+  });
+
+  test("user preference: custom provider listed in userFlatRate is flat-rate", () => {
+    assert.equal(
+      isFlatRateProvider("my-ollama-proxy", { userFlatRate: ["my-ollama-proxy"] }),
+      true,
+    );
+  });
+
+  test("user preference: case-insensitive match against userFlatRate list", () => {
+    assert.equal(
+      isFlatRateProvider("My-Proxy", { userFlatRate: ["my-proxy"] }),
+      true,
+    );
+    assert.equal(
+      isFlatRateProvider("my-proxy", { userFlatRate: ["MY-PROXY"] }),
+      true,
+    );
+  });
+
+  test("user preference: provider not in userFlatRate list is not flat-rate", () => {
+    assert.equal(
+      isFlatRateProvider("other-proxy", { userFlatRate: ["my-proxy"] }),
+      false,
+    );
+  });
+
+  test("combined signals: built-in list wins even when context is empty", () => {
+    assert.equal(
+      isFlatRateProvider("claude-code", { authMode: "apiKey", userFlatRate: [] }),
+      true,
+    );
+  });
+
+  test("combined signals: externalCli auto-detection wins alongside userFlatRate miss", () => {
+    assert.equal(
+      isFlatRateProvider("my-cli", {
+        authMode: "externalCli",
+        userFlatRate: ["a-different-cli"],
+      }),
+      true,
+    );
+  });
+});
+
+describe("buildFlatRateContext()", () => {
+  test("builds a context from ctx.modelRegistry.getProviderAuthMode + prefs", () => {
+    const ctx = {
+      modelRegistry: {
+        getProviderAuthMode: (p: string) =>
+          p === "my-cli" ? "externalCli" : "apiKey",
+      },
+    };
+    const prefs = { flat_rate_providers: ["my-proxy"] };
+
+    const ctxForCli = buildFlatRateContext("my-cli", ctx, prefs);
+    assert.equal(ctxForCli.authMode, "externalCli");
+    assert.deepEqual(ctxForCli.userFlatRate, ["my-proxy"]);
+    assert.equal(isFlatRateProvider("my-cli", ctxForCli), true);
+
+    const ctxForProxy = buildFlatRateContext("my-proxy", ctx, prefs);
+    assert.equal(ctxForProxy.authMode, "apiKey");
+    assert.equal(isFlatRateProvider("my-proxy", ctxForProxy), true);
+
+    const ctxForOther = buildFlatRateContext("anthropic", ctx, prefs);
+    assert.equal(ctxForOther.authMode, "apiKey");
+    assert.equal(isFlatRateProvider("anthropic", ctxForOther), false);
+  });
+
+  test("survives missing ctx and missing prefs", () => {
+    const empty = buildFlatRateContext("anything");
+    assert.equal(empty.authMode, undefined);
+    assert.equal(empty.userFlatRate, undefined);
+    assert.equal(isFlatRateProvider("anything", empty), false);
+  });
+
+  test("survives a registry lookup that throws", () => {
+    const ctx = {
+      modelRegistry: {
+        getProviderAuthMode: () => {
+          throw new Error("registry boom");
+        },
+      },
+    };
+    const result = buildFlatRateContext("anything", ctx);
+    // Error must be swallowed — authMode left undefined, function returns.
+    assert.equal(result.authMode, undefined);
+  });
+
+  test("registry returning a non-canonical auth mode is ignored", () => {
+    const ctx = {
+      modelRegistry: {
+        getProviderAuthMode: () => "weird-mode",
+      },
+    };
+    const result = buildFlatRateContext("anything", ctx);
+    assert.equal(result.authMode, undefined);
+  });
+});

src/resources/extensions/gsd/tests/preferences.test.ts

@@ -134,6 +134,53 @@ test("invalid value types produce errors and fall back to undefined", () => {
   }
 });
 
+test("flat_rate_providers: accepts string array", () => {
+  const { errors, preferences } = validatePreferences({
+    flat_rate_providers: ["my-proxy", "private-cli"],
+  });
+  assert.equal(errors.length, 0);
+  assert.deepEqual(preferences.flat_rate_providers, ["my-proxy", "private-cli"]);
+});
+
+test("flat_rate_providers: trims whitespace and drops empty entries", () => {
+  const { errors, preferences } = validatePreferences({
+    flat_rate_providers: ["  my-proxy  ", "", "   ", "private-cli"],
+  });
+  assert.equal(errors.length, 0);
+  assert.deepEqual(preferences.flat_rate_providers, ["my-proxy", "private-cli"]);
+});
+
+test("flat_rate_providers: non-array rejected", () => {
+  const { errors } = validatePreferences({
+    flat_rate_providers: "my-proxy" as any,
+  });
+  assert.ok(
+    errors.some(e => e.includes("flat_rate_providers")),
+    "should error on non-array value",
+  );
+});
+
+test("flat_rate_providers: non-string elements rejected", () => {
+  const { errors } = validatePreferences({
+    flat_rate_providers: ["ok", 123 as any, "also-ok"],
+  });
+  assert.ok(
+    errors.some(e => e.includes("flat_rate_providers")),
+    "should error when array contains non-strings",
+  );
+});
+
+test("flat_rate_providers is a recognized preference key (no warning)", () => {
+  const { warnings } = validatePreferences({
+    flat_rate_providers: ["my-proxy"],
+  });
+  assert.equal(
+    warnings.filter(w => w.includes("flat_rate_providers")).length,
+    0,
+    "flat_rate_providers must be in KNOWN_PREFERENCE_KEYS",
+  );
+});
+
 test("valid values pass through correctly", () => {
   const { preferences: p1 } = validatePreferences({ budget_enforcement: "halt" });
   assert.equal(p1.budget_enforcement, "halt");