aicodeman 1.43.0 → 1.44.0

package/dist/web/routes/session-routes.js

@@ -3,7 +3,7 @@
  * Covers session CRUD, input/output, terminal buffer, quick-start, quick-run,
  * auto-clear, auto-compact, image watcher, flicker filter, and logout.
  */
-import { join, dirname, extname, basename } from 'node:path';
+import { join, dirname, extname, basename, resolve as resolvePath } from 'node:path';
 import { homedir } from 'node:os';
 import { existsSync, statSync, mkdirSync, writeFileSync } from 'node:fs';
 import { execFile } from 'node:child_process';
@@ -17,7 +17,7 @@ import { Session, cliTakesSessionModel, isAltScreenStripMode, isExternalCliMode,
 import { SseEvent } from '../sse-events.js';
 import { webviewCapabilities } from '../../webview-capabilities.js';
 import { htmlViewCapabilities } from '../../html-view-capabilities.js';
-import { CreateSessionSchema, SessionNameSchema, SessionColorSchema, RunPromptSchema, SessionInputWithLimitSchema, ResizeSchema, AutoClearSchema, AutoCompactSchema, AutoResumeSchema, PinSessionSchema, ImageWatcherSchema, FlickerFilterSchema, QuickRunSchema, QuickStartSchema, InteractiveStartSchema, SessionOrderUpdateSchema, SessionWaitQuerySchema, SessionWaitOutputQuerySchema, CustomModelSelectionSchema, } from '../schemas.js';
+import { CreateSessionSchema, SessionNameSchema, SessionColorSchema, RunPromptSchema, SessionInputWithLimitSchema, ResizeSchema, AutoClearSchema, AutoCompactSchema, AutoResumeSchema, KeepWarmSchema, PinSessionSchema, ImageWatcherSchema, FlickerFilterSchema, QuickRunSchema, QuickStartSchema, InteractiveStartSchema, SessionOrderUpdateSchema, SessionWaitQuerySchema, SessionWaitOutputQuerySchema, CustomModelSelectionSchema, } from '../schemas.js';
 import { readCustomModelHosts } from '../../custom-model-hosts.js';
 import { applyCustomModelInjection, removeConfigDir } from '../../custom-model-injection-apply.js';
 import { getLlamaSwapStatus, triggerLlamaSwapLoad, exceedsSafeContextFloor, CLAUDE_MIN_SAFE_CONTEXT_TOKENS, } from './custom-model-routes.js';
@@ -27,7 +27,7 @@ import { TabLayoutValidationError } from '../../tab-layout.js';
 import { sessionWaits, resolveWaitSignals, sessionHookOptions, signalForStatus, WaitCapacityError, } from '../session-wait-registry.js';
 import { RemoteWakeRegistry, REMOTE_WAKE_REQUEST_READY_TIMEOUT_MS, createDefaultRemoteWakeDeps, isProbeable, } from '../../remote-wake.js';
 import { clampWaitMs, MAX_BUFFER_SCAN_BYTES } from '../../config/agent-wait.js';
-import { autoConfigureRalph, canAccessOwned, CASES_DIR, findPersistedSessionOrFail, findSessionOrFail, getAuthUser, isAdmin, isPlainPromptInput, isWorkingDirAllowed, ownerFor, parseBody, persistAndBroadcastSession, resolveAgentCaseOrigin, resolveCasesDir, resolveParentSessionId, sessionCapacityMessage, SETTINGS_PATH, validatePathWithinBase, } from '../route-helpers.js';
+import { autoConfigureRalph, canAccessOwned, CASES_DIR, findPersistedSessionOrFail, findSessionOrFail, getAuthUser, isAdmin, isPlainPromptInput, isWorkingDirAllowed, ownerFor, parseBody, persistAndBroadcastSession, readJsonConfig, resolveAgentCaseOrigin, resolveCasesDir, resolveParentSessionId, sessionCapacityMessage, SETTINGS_PATH, validatePathWithinBase, } from '../route-helpers.js';
 import { buildAgentCaseMarker, writeAgentCaseMarker } from '../../agent-case-marker.js';
 import { canUsernameRunPrivilegedCommands, resolveClaudeModeForUsername } from '../../user-store.js';
 import { clampEnvOverridesForOwner } from '../../session-env-clamp.js';
@@ -65,6 +65,41 @@ import { UPLOADS_DIR } from '../paste-image-gc.js';
 // Path to linked-cases registry (same file used by case-routes resolveCasePath)
 const LINKED_CASES_FILE = dataPath('linked-cases.json');
 const CODEMAN_CONFIG_DIR = getDataDir();
+const SAFE_CASE_NAME = /^[a-zA-Z0-9_-]+$/;
+/** `<repo>/.claude/worktrees/<name>`: the layout Claude Code's own worktree feature creates. */
+const CLAUDE_WORKTREE_PATH = /^(.*)\/\.claude\/worktrees\/([^/]+)\/?$/;
+/** Did the committed layout put this session in a named group (not Ungrouped)? */
+function landedInGroup(layout, sessionId) {
+    return !!layout?.groups.some((group) => group.refs.some((ref) => ref.kind === 'session' && ref.id === sessionId));
+}
+/**
+ * The case a POST /api/sessions `workingDir` belongs to, for its default session
+ * group: a direct child of the caller's case space, or (admin / single-user, as
+ * GET /api/cases lists them) a linked case's exact path, or a Claude worktree
+ * (`<case>/.claude/worktrees/<name>`) of either. Lexical only: the browser sends
+ * the path the case list gave it, and this must never touch a possibly-dead
+ * mount. Anything else is no case, which keeps today's placement.
+ */
+async function inferLocalCaseName(req, workingDir) {
+    // The Git worktrees modal launches Claude through this route in the worktree, and every other CLI
+    // through quick-start with the case name: both are sessions of that case.
+    const resolved = resolvePath(workingDir);
+    const target = CLAUDE_WORKTREE_PATH.exec(resolved)?.[1] || resolved;
+    const user = getAuthUser(req);
+    if (dirname(target) === resolvePath(resolveCasesDir(user))) {
+        const name = basename(target);
+        if (SAFE_CASE_NAME.test(name))
+            return name;
+    }
+    if (isMultiUserMode() && !isAdmin(req))
+        return undefined;
+    const linked = await readJsonConfig(LINKED_CASES_FILE, 'linked cases', {});
+    for (const [name, path] of Object.entries(linked)) {
+        if (SAFE_CASE_NAME.test(name) && typeof path === 'string' && resolvePath(path) === target)
+            return name;
+    }
+    return undefined;
+}
 // Pre-compiled regex for terminal buffer cleaning (avoids per-request compilation)
 // eslint-disable-next-line no-control-regex
 const CLAUDE_BANNER_PATTERN = /\x1b\[1mClaud/;
@@ -1149,9 +1184,13 @@ options = {}) {
             owner,
             parentSessionId: resolveParentSessionId(ctx, req, body.parentSessionId, owner),
         });
-        const tabLayout = body.tabGroupId
-            ? await ctx.addSession(session, { tabGroupId: body.tabGroupId })
-            : await ctx.addSession(session);
+        // Only a named workingDir: without one the session starts in the server's own cwd, which is no case.
+        const placementCase = remote || !body.workingDir ? undefined : await inferLocalCaseName(req, workingDir);
+        const placement = {
+            ...(body.tabGroupId ? { tabGroupId: body.tabGroupId } : {}),
+            ...(placementCase ? { caseName: placementCase } : {}),
+        };
+        const tabLayout = Object.keys(placement).length > 0 ? await ctx.addSession(session, placement) : await ctx.addSession(session);
         ctx.store.incrementSessionsCreated();
         ctx.persistSessionState(session);
         await ctx.setupSessionListeners(session);
@@ -1166,9 +1205,13 @@ options = {}) {
         // Avoids serializing 2-3MB of terminal+text buffers per session creation.
         const lightState = ctx.getSessionStateWithRespawn(session);
         ctx.broadcast(SseEvent.SessionCreated, lightState);
-        // A grouped creation also returns the layout that placed it, so the browser
-        // draws the tab inside its group at once instead of after a re-read.
-        return { session: lightState, ...(body.tabGroupId ? { tabLayout } : {}) };
+        // A grouped creation (asked for, or its case's default group) also returns the
+        // layout that placed it, so the browser draws the tab inside its group at once
+        // instead of after a re-read.
+        return {
+            session: lightState,
+            ...(body.tabGroupId || landedInGroup(tabLayout, session.id) ? { tabLayout } : {}),
+        };
     });
     // ========== Rename Session ==========
     app.put('/api/sessions/:id/name', async (req) => {
@@ -1246,6 +1289,7 @@ options = {}) {
             return createErrorResponse(ApiErrorCode.NOT_FOUND, 'Model endpoint not found');
         }
         const contextLength = endpoint.modelContextLengths?.[body.modelId];
+        const slotCount = endpoint.modelSlotCounts?.[body.modelId];
         // Some CLIs (today: only claude) carry enough of their own fixed system-prompt/tool-
         // schema overhead that a small enough real context guarantees a first-message failure
         // no matter what CLAUDE_CODE_MAX_CONTEXT_TOKENS says — confirmed live at ~36.4K tokens
@@ -1255,12 +1299,13 @@ options = {}) {
         // `confirmed`, which still means both) — NOT by `confirmedSwap`: this warning is
         // about the caller's own session, and the swap warning below is about someone
         // else's, so an answer to one is not consent to the other.
-        if (!(body.confirmed || body.confirmedContext) && exceedsSafeContextFloor(entry, contextLength)) {
+        if (!(body.confirmed || body.confirmedContext) && exceedsSafeContextFloor(entry, contextLength, slotCount)) {
             return {
                 requiresContextWarning: true,
                 modelId: body.modelId,
                 contextLength,
                 minSafeContextTokens: CLAUDE_MIN_SAFE_CONTEXT_TOKENS,
+                ...(slotCount && slotCount > 1 ? { slotCount } : {}),
             };
         }
         // llama.cpp runs exactly one model at a time; llama-swap unloads and reloads it on
@@ -3089,6 +3134,32 @@ options = {}) {
             },
         };
     });
+    // ========== Prompt-cache keep-warm ==========
+    // Per-session opt-in for the keep-alive nudge (prompt-cache-keepwarm.ts). `enabled: null`
+    // clears the choice so the app-wide default applies again. Refused for a CLI that reports
+    // no cache telemetry on its statusline: without `expires_at` there is nothing to schedule.
+    app.post('/api/sessions/:id/keep-warm', async (req) => {
+        const { id } = req.params;
+        const body = parseBody(KeepWarmSchema, req.body, 'Invalid request body');
+        const session = findSessionOrFail(ctx, id, req);
+        if (!getCli(session.mode)?.capabilities.statusLineTelemetry) {
+            return createErrorResponse(ApiErrorCode.INVALID_INPUT, 'Prompt-cache keep-warm needs the cache telemetry this CLI does not report');
+        }
+        session.setKeepWarmEnabled(body.enabled ?? undefined);
+        // Re-evaluate BEFORE the state broadcast and the response: both carry `keepWarm`, and a
+        // page that received the previous status would overwrite the one the toggle just produced.
+        await ctx.keepWarm.schedule(id);
+        persistAndBroadcastSession(ctx, session);
+        return {
+            success: true,
+            data: {
+                keepWarm: {
+                    enabled: session.keepWarmEnabled ?? null,
+                    status: session.keepWarm,
+                },
+            },
+        };
+    });
     // ========== Auto-Resume (usage-limit pause) ==========
     app.post('/api/sessions/:id/auto-resume', async (req) => {
         const { id } = req.params;
@@ -3688,6 +3759,7 @@ options = {}) {
             if (!cmEndpoint)
                 return createErrorResponse(ApiErrorCode.NOT_FOUND, 'Model endpoint not found');
             const cmContextLength = cmEndpoint.modelContextLengths?.[customModel.modelId];
+            const cmSlotCount = cmEndpoint.modelSlotCounts?.[customModel.modelId];
             // See the dedicated route's own comment for the full reasoning: some CLIs' own fixed
             // overhead can exceed a small enough real context on the very first message,
             // regardless of contextLengthVar. Warn before creating a session that's certain to
@@ -3695,12 +3767,13 @@ options = {}) {
             // See the dedicated route above for why this reads `confirmedContext` and never
             // `confirmedSwap`.
             if (!(customModel.confirmed || customModel.confirmedContext) &&
-                exceedsSafeContextFloor(cmEntry, cmContextLength)) {
+                exceedsSafeContextFloor(cmEntry, cmContextLength, cmSlotCount)) {
                 return {
                     requiresContextWarning: true,
                     modelId: customModel.modelId,
                     contextLength: cmContextLength,
                     minSafeContextTokens: CLAUDE_MIN_SAFE_CONTEXT_TOKENS,
+                    ...(cmSlotCount && cmSlotCount > 1 ? { slotCount: cmSlotCount } : {}),
                 };
             }
             // See the dedicated route's own comment for the full reasoning: llama.cpp runs one
@@ -3834,7 +3907,7 @@ options = {}) {
                 session.ralphTracker.enableAutoEnable(); // Allow re-enabling on restart
             }
         }
-        const tabLayout = tabGroupId ? await ctx.addSession(session, { tabGroupId }) : await ctx.addSession(session);
+        const tabLayout = await ctx.addSession(session, { caseName, ...(tabGroupId ? { tabGroupId } : {}) });
         ctx.store.incrementSessionsCreated();
         ctx.persistSessionState(session);
         await ctx.setupSessionListeners(session);
@@ -3920,7 +3993,7 @@ options = {}) {
                 caseName,
                 ...(worktree ? { worktree, workingDir: workspacePath } : {}),
                 ...(customModel ? { modelSwapInProgress: qsCustomModelSwapInProgress } : {}),
-                ...(tabGroupId ? { tabLayout } : {}),
+                ...(tabGroupId || landedInGroup(tabLayout, session.id) ? { tabLayout } : {}),
             };
         }
         catch (err) {
@@ -4045,8 +4118,6 @@ options = {}) {
         }
         return sawNonCli;
     }
-    /** `<repo>/.claude/worktrees/<name>` — the layout Claude Code's own worktree feature creates. */
-    const CLAUDE_WORKTREE_PATH = /^(.*)\/\.claude\/worktrees\/([^/]+)\/?$/;
     /**
      * Recover cwd / branch / worktree from a transcript chunk.
      *