fix: add concurrency controls for multiple sessions using the same provider (#1069)

* fix: add concurrency controls for multiple sessions using the same provider

Adds OS-inspired scheduling primitives (from HiveMind/AIMD research) to prevent
concurrent sessions from the same provider from experiencing slowdowns, random
stops, and cascading failures.

Server-side:
- Health check skips OpenCode restart when sessions are actively busy — a busy
  server under concurrent load can fail the health check timeout without being
  dead. Staleness guard forces restart if unhealthy+busy persists >2 minutes.
- Upstream SSE stall timeout scaled from 20s to 60s to avoid unnecessary
  reconnections when multiple sessions are waiting for LLM responses.

Client-side (HiveMind primitives, arXiv:2604.17111):
- Transparent retry with exponential backoff (1s→2s→4s, max 32s) for
  429/502/503/504 errors — the #1 most effective primitive from the paper.
- Circuit breaker: opens after 3 consecutive retryable errors, cooldown
  doubles each trip (30s→60s→120s, capped 128s), matching TCP AIMD.
- Per-provider session tracking with TTL eviction (1h idle sweep).
- Fetch-level retry gated on AbortError/TypeError only (not DNS failures).

Refs github-code-review skill findings (all 8 issues resolved).

* fix: use definite assignment assertion for response variable

Fixes TS2454: Variable 'response' is used before being assigned
in strict mode. The for-loop body always assigns it on every path
that reaches the post-loop code, but TS can't prove that.

* fix: add cleanupSession to error paths and remove unreachable code

P1 fixes (Greptile review):
- cleanupSession called on fetch error throw path
- cleanupSession called on non-retryable HTTP error throw path
- Removed unreachable post-loop code (loop always terminates via return or throw)

Adds explicit post-loop throw to satisfy TypeScript strict return check.

* fix: address Greptile review feedback on concurrent session controls

Removes client-side session tracking that leaked on normal completion paths.

The session tracking was redundant — the server-side health check already reads from

sessionRuntime.getSessionActivitySnapshot() for busy-session detection.

Changes:

- Remove activeSessions Set and all session-tracking functions from provider-tracker

- Remove trackSessionStarted/cleanupSession calls from client.ts

- Remove unreachable (response as Response) block after retry loop

- Make upstreamStallTimeoutMs conditional: 60s when >1 sessions, 20s otherwise

Refs #1069

* fix: enforce dynamic concurrency safeguards

---------

Co-authored-by: Bohdan Triapitsyn <artmore@protonmail.com>

packages/web/server/index.js

@@ -35,6 +35,8 @@ import {
   createGlobalUiEventBroadcaster,
   createGlobalMessageStreamHub,
   createMessageStreamWsRuntime,
+  DEFAULT_UPSTREAM_STALL_TIMEOUT_MS,
+  UPSTREAM_STALL_TIMEOUT_CONCURRENT_MS,
 } from './lib/event-stream/index.js';
 import { createFsSearchRuntime as createFsSearchRuntimeFactory } from './lib/fs/search.js';
 import { createOpenCodeLifecycleRuntime } from './lib/opencode/lifecycle.js';
@@ -381,6 +383,17 @@ const sessionRuntime = createSessionRuntime({
   broadcastEvent: broadcastGlobalUiEvent,
 });
 
+const getActiveSessionCount = () => {
+  const snapshot = sessionRuntime.getSessionActivitySnapshot();
+  return Object.values(snapshot).filter((entry) => entry.type === 'busy').length;
+};
+
+const getUpstreamStallTimeoutMs = () => (
+  getActiveSessionCount() > 1
+    ? UPSTREAM_STALL_TIMEOUT_CONCURRENT_MS
+    : DEFAULT_UPSTREAM_STALL_TIMEOUT_MS
+);
+
 const projectConfigRuntime = createProjectConfigRuntime({
   fsPromises,
   path,
@@ -655,6 +668,7 @@ const setAutoAcceptSession = (...args) => notificationTriggerRuntime.setAutoAcce
 const globalMessageStreamHub = createGlobalMessageStreamHub({
   buildOpenCodeUrl,
   getOpenCodeAuthHeaders,
+  upstreamStallTimeoutMs: getUpstreamStallTimeoutMs,
 });
 
 const openCodeWatcherRuntime = createOpenCodeWatcherRuntime({
@@ -881,6 +895,7 @@ const openCodeLifecycleRuntime = createOpenCodeLifecycleRuntime({
   buildAugmentedPath,
   buildManagedOpenCodePath,
   getManagedOpenCodeShellEnvSnapshot: getLoginShellEnvSnapshot,
+  getActiveSessionCount,
 });
 
 const restartOpenCode = (...args) => openCodeLifecycleRuntime.restartOpenCode(...args);
@@ -1188,6 +1203,7 @@ async function main(options = {}) {
     globalEventHub: globalMessageStreamHub,
     processForwardedEventPayload,
     messageStreamWsClients: uiNotificationWsClients,
+    upstreamStallTimeoutMs: getUpstreamStallTimeoutMs,
     terminalHeartbeatIntervalMs: TERMINAL_INPUT_WS_HEARTBEAT_INTERVAL_MS,
     terminalRebindWindowMs: TERMINAL_INPUT_WS_REBIND_WINDOW_MS,
     terminalMaxRebindsPerWindow: TERMINAL_INPUT_WS_MAX_REBINDS_PER_WINDOW,