Merge branch 'feature/concurrency-fixes' into predev

# Conflicts:
#	backend-handoff.md

3 files changed, 195 insertions, 1 deletions

diff --git a/src/app/App.svelte b/src/app/App.svelte
index e508203..b2cfd2d 100644
--- a/src/app/App.svelte
+++ b/src/app/App.svelte
@@ -76,6 +76,7 @@
 		type DeleteConcurrencyLimit,
 		type LoadConcurrencyLimits,
 		type LoadConcurrencyStatus,
+		type SaveConcurrencyCooldown,
 		type SaveConcurrencyLimit,
 	} from "../features/concurrency";
 	import type { ChatStore } from "../features/chat";
@@ -491,6 +492,8 @@
 	const deleteConcurrencyLimit: DeleteConcurrencyLimit = (providerId) =>
 		store.deleteConcurrencyLimit(providerId);
 	const loadConcurrencyStatus: LoadConcurrencyStatus = () => store.concurrencyStatus();
+	const saveConcurrencyCooldown: SaveConcurrencyCooldown = (providerId, cooldownMs) =>
+		store.setConcurrencyCooldown(providerId, cooldownMs);
 </script>
 
 <main class="relative flex h-screen overflow-hidden">
@@ -841,6 +844,7 @@
 			saveLimit={saveConcurrencyLimit}
 			deleteLimit={deleteConcurrencyLimit}
 			loadStatus={loadConcurrencyStatus}
+			saveCooldown={saveConcurrencyCooldown}
 		/>
 	{/if}
 {/snippet}
diff --git a/src/app/store.svelte.ts b/src/app/store.svelte.ts
index 82d755d..22b0a25 100644
--- a/src/app/store.svelte.ts
+++ b/src/app/store.svelte.ts
@@ -55,12 +55,14 @@ import {
 import type { ChatStore, HistorySync, MetricsSync } from "../features/chat";
 import { createChatStore } from "../features/chat";
 import type {
+  ConcurrencyCooldownResult,
   ConcurrencyDeleteResult,
   ConcurrencyLimitResult,
   ConcurrencyLimitsResult,
   ConcurrencyStatusResult,
 } from "../features/concurrency";
 import {
+  normalizeConcurrencyCooldown,
   normalizeConcurrencyLimit,
   normalizeConcurrencyLimits,
   normalizeConcurrencyStatus,
@@ -452,11 +454,29 @@ export interface AppStore {
   /**
    * Fetch live concurrency status for every provider with a configured limit
    * (`GET /concurrency/status`): in-flight slots held, agents queued, and a paused
-   * state with a `pausedUntil` epoch-ms when a 429 backoff is in effect. Returns
+   * state with a `pausedUntil` epoch-ms when a 429 backoff is in effect. Each
+   * entry also carries the per-slot release `cooldownMs` + an `autoReduced` flag
+   * (true when a 429 auto-reduced the limit by 1; the FE renders a banner). Returns
    * an empty list when the extension isn't loaded (`{ providers: [] }`).
    */
   concurrencyStatus(): Promise<ConcurrencyStatusResult>;
   /**
+   * Fetch the per-slot release cooldown (ms) for one provider
+   * (`GET /concurrency/cooldown/:providerId`). `404` (no concurrency config at
+   * all) and `503` (extension not loaded) both surface as `ok: false`.
+   */
+  getConcurrencyCooldown(providerId: string): Promise<ConcurrencyCooldownResult>;
+  /**
+   * Set the per-slot release cooldown (ms) for one provider
+   * (`PUT /concurrency/cooldown/:providerId`, body `{ cooldownMs }`). `cooldownMs`
+   * must be a non-negative integer (0 = no cooldown / instant re-admission); an
+   * invalid body is `400`. Persists + applies to subsequently recycled slots.
+   */
+  setConcurrencyCooldown(
+    providerId: string,
+    cooldownMs: number,
+  ): Promise<ConcurrencyCooldownResult>;
+  /**
    * A critical error that blocks normal operation (e.g. the cross-device tab
    * restore fetch failed). When non-null, a full-screen modal is shown with the
    * error details. Cleared by `clearFatalError` (the modal's dismiss button).
@@ -1989,6 +2009,64 @@ export function createAppStore(opts?: CreateAppStoreOptions): AppStore {
       }
     },
 
+    async getConcurrencyCooldown(providerId: string): Promise<ConcurrencyCooldownResult> {
+      try {
+        const res = await fetchImpl(
+          `${httpBase}/concurrency/cooldown/${encodeURIComponent(providerId)}`,
+        );
+        if (!res.ok) {
+          const errBody = (await res.json().catch(() => null)) as { error?: string } | null;
+          return {
+            ok: false,
+            error: errBody?.error ?? `Get concurrency cooldown failed (HTTP ${res.status})`,
+          };
+        }
+        const data = normalizeConcurrencyCooldown(await res.json());
+        if (data === null) {
+          return { ok: false, error: "Malformed concurrency cooldown response" };
+        }
+        return { ok: true, providerId: data.providerId, cooldownMs: data.cooldownMs };
+      } catch (err) {
+        return {
+          ok: false,
+          error: err instanceof Error ? err.message : "Get concurrency cooldown request failed",
+        };
+      }
+    },
+
+    async setConcurrencyCooldown(
+      providerId: string,
+      cooldownMs: number,
+    ): Promise<ConcurrencyCooldownResult> {
+      try {
+        const res = await fetchImpl(
+          `${httpBase}/concurrency/cooldown/${encodeURIComponent(providerId)}`,
+          {
+            method: "PUT",
+            headers: { "content-type": "application/json" },
+            body: JSON.stringify({ cooldownMs }),
+          },
+        );
+        if (!res.ok) {
+          const errBody = (await res.json().catch(() => null)) as { error?: string } | null;
+          return {
+            ok: false,
+            error: errBody?.error ?? `Set concurrency cooldown failed (HTTP ${res.status})`,
+          };
+        }
+        const data = normalizeConcurrencyCooldown(await res.json());
+        if (data === null) {
+          return { ok: false, error: "Malformed concurrency cooldown response" };
+        }
+        return { ok: true, providerId: data.providerId, cooldownMs: data.cooldownMs };
+      } catch (err) {
+        return {
+          ok: false,
+          error: err instanceof Error ? err.message : "Set concurrency cooldown request failed",
+        };
+      }
+    },
+
     async loadSystemPrompt(): Promise<SystemPromptLoadResult> {
       try {
         const res = await fetchImpl(`${httpBase}/system-prompt`);
diff --git a/src/app/store.test.ts b/src/app/store.test.ts
index 1048d87..a945ea7 100644
--- a/src/app/store.test.ts
+++ b/src/app/store.test.ts
@@ -1462,6 +1462,20 @@ describe("createAppStore", () => {
       if (url.includes("/concurrency/limits/") && method === "DELETE") {
         return new Response(JSON.stringify({ ok: true, providerId: "umans" }), { status: 200 });
       }
+      if (url.includes("/concurrency/cooldown/") && method === "GET") {
+        return new Response(JSON.stringify({ providerId: "umans", cooldownMs: 350 }), {
+          status: 200,
+        });
+      }
+      if (url.includes("/concurrency/cooldown/") && method === "PUT") {
+        const seg = url.slice(
+          url.lastIndexOf("/concurrency/cooldown/") + "/concurrency/cooldown/".length,
+        );
+        const body = init?.body ? JSON.parse(init.body as string) : {};
+        return new Response(JSON.stringify({ providerId: seg, cooldownMs: body.cooldownMs ?? 0 }), {
+          status: 200,
+        });
+      }
       return base(input, init);
     };
   }
@@ -1645,11 +1659,15 @@ describe("createAppStore", () => {
       inFlight: 2,
       queued: 1,
       paused: false,
+      cooldownMs: 350,
+      autoReduced: false,
     });
     expect(result.providers[1]).toMatchObject({
       providerId: "openai-compat",
       paused: true,
       pausedUntil: 1_719_408_000_000,
+      cooldownMs: 350,
+      autoReduced: false,
     });
     store.dispose();
   });
@@ -1667,6 +1685,100 @@ describe("createAppStore", () => {
     store.dispose();
   });
 
+  it("getConcurrencyCooldown loads + coerces the cooldown", async () => {
+    const store = createAppStore({
+      socketFactory: () => fakeSocket(),
+      fetchImpl: concurrencyFetchImpl(),
+      localStorage: createFakeStorage(),
+    });
+    const result = await store.getConcurrencyCooldown("umans");
+    expect(result.ok).toBe(true);
+    if (!result.ok) throw new Error("unreachable");
+    expect(result.providerId).toBe("umans");
+    expect(result.cooldownMs).toBe(350);
+    store.dispose();
+  });
+
+  it("getConcurrencyCooldown surfaces a 404 (no concurrency config) as ok:false", async () => {
+    const store = createAppStore({
+      socketFactory: () => fakeSocket(),
+      fetchImpl: async (input) => {
+        const url =
+          typeof input === "string" ? input : input instanceof URL ? input.href : input.url;
+        if (url.includes("/concurrency/cooldown/")) {
+          return new Response(
+            JSON.stringify({ error: "No concurrency configuration for this provider" }),
+            {
+              status: 404,
+            },
+          );
+        }
+        return fakeFetchImpl()(input);
+      },
+      localStorage: createFakeStorage(),
+    });
+    const result = await store.getConcurrencyCooldown("ghost");
+    expect(result.ok).toBe(false);
+    if (result.ok) throw new Error("unreachable");
+    expect(result.error).toContain("No concurrency configuration");
+    store.dispose();
+  });
+
+  it("setConcurrencyCooldown PUTs { cooldownMs } + returns the echoed value", async () => {
+    const calls: { url: string; method: string; body: unknown }[] = [];
+    const store = createAppStore({
+      socketFactory: () => fakeSocket(),
+      fetchImpl: async (input, init) => {
+        const url =
+          typeof input === "string" ? input : input instanceof URL ? input.href : input.url;
+        const method = init?.method ?? "GET";
+        calls.push({ url, method, body: init?.body ? JSON.parse(init.body as string) : null });
+        if (url.includes("/concurrency/cooldown/") && method === "PUT") {
+          const body = init?.body ? JSON.parse(init.body as string) : {};
+          return new Response(
+            JSON.stringify({ providerId: "umans", cooldownMs: body.cooldownMs }),
+            { status: 200 },
+          );
+        }
+        return fakeFetchImpl()(input, init);
+      },
+      localStorage: createFakeStorage(),
+    });
+    const result = await store.setConcurrencyCooldown("umans", 500);
+    expect(result.ok).toBe(true);
+    if (!result.ok) throw new Error("unreachable");
+    expect(result.cooldownMs).toBe(500);
+    const cooldownCall = calls.find(
+      (c) => c.url.includes("/concurrency/cooldown/") && c.method === "PUT",
+    );
+    expect(cooldownCall?.url).toContain("/concurrency/cooldown/umans");
+    expect(cooldownCall?.body).toEqual({ cooldownMs: 500 });
+    store.dispose();
+  });
+
+  it("setConcurrencyCooldown surfaces a 400 (invalid body) as ok:false", async () => {
+    const store = createAppStore({
+      socketFactory: () => fakeSocket(),
+      fetchImpl: async (input, init) => {
+        const url =
+          typeof input === "string" ? input : input instanceof URL ? input.href : input.url;
+        if (url.includes("/concurrency/cooldown/") && init?.method === "PUT") {
+          return new Response(
+            JSON.stringify({ error: "Body must be { cooldownMs: <non-negative integer> }" }),
+            { status: 400 },
+          );
+        }
+        return fakeFetchImpl()(input, init);
+      },
+      localStorage: createFakeStorage(),
+    });
+    const result = await store.setConcurrencyCooldown("umans", -1);
+    expect(result.ok).toBe(false);
+    if (result.ok) throw new Error("unreachable");
+    expect(result.error).toContain("non-negative integer");
+    store.dispose();
+  });
+
   // ── Conversation status: `queued` (CR-13 — waiting for a concurrency slot) ────
 
   it("conversation.statusChanged 'queued' sets the status (tab spinner) without opening a duplicate tab", () => {