Merge pull request #755: feat(custom-model): DeepSeek Harness injection through a per-session patch

src/web/routes/session-routes.ts

@@ -7,7 +7,7 @@
 import { claudeProjectDirName } from '../../case-rename.js';
 import { FastifyInstance, type FastifyRequest } from 'fastify';
 import { z } from 'zod';
-import { join, dirname, extname, basename, resolve as resolvePath } from 'node:path';
+import { join, dirname, extname, basename, isAbsolute, 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';
@@ -127,7 +127,7 @@ import { agentInbox } from '../agent-inbox.js';
 import { canUsernameRunPrivilegedCommands, resolveClaudeModeForUsername } from '../../user-store.js';
 import { clampEnvOverridesForOwner } from '../../session-env-clamp.js';
 import { enabledClis, getCli } from '../../config/cli-registry/registry.js';
-import type { AgentSkillDir, NewlineSequence } from '../../config/cli-registry/types.js';
+import type { AgentSkillDir, CliEntry, NewlineSequence } from '../../config/cli-registry/types.js';
 import { resolveCliLaunchError } from '../../utils/cli-launcher.js';
 import { applyLaunchDefaults } from '../launch-defaults.js';
 import { legacyConfigForMode } from '../../session-cli-registry-bridge.js';
@@ -231,6 +231,36 @@ function landedInGroup(layout: TabLayout | undefined, sessionId: string): boolea
   return !!layout?.groups.some((group) => group.refs.some((ref) => ref.kind === 'session' && ref.id === sessionId));
 }
 
+/**
+ * Guard a session-supplied configDir home BEFORE `applyCustomModelInjection` runs.
+ *
+ * The apply resolves the CLI's real home from this session's env override and then runs
+ * synchronous `existsSync`/`mkdirSync` on it (deepseek `DSH_HOME`, and any future
+ * `linkFromRealHome` recipe). A path on an unreachable network mount makes a synchronous
+ * stat wait forever, and this runs INSIDE a request handler, so it would freeze the whole
+ * web server (CLAUDE.md, the #516 rule on user-chosen paths). A relative home is left to
+ * the apply, which already refuses to join non-absolute values.
+ *
+ * Probe the session's own home with `probePathKind(..., { pastCap: true })` first: on
+ * `'unknown'` (a dead mount that never answered) hand the apply a lookup that hides that
+ * one env var, so linking falls through to the server's own environment and the unresponsive
+ * path is never touched. Any other entry's lookup passes through untouched.
+ */
+async function guardSessionConfigDirHome(
+  entry: Pick<CliEntry, 'capabilities'>,
+  baseLookup: (envVar: string) => string | undefined
+): Promise<(envVar: string) => string | undefined> {
+  const recipe = entry.capabilities.customModelInjection;
+  if (recipe?.kind !== 'configDir' || !recipe.linkFromRealHome?.length) return baseLookup;
+  const dirEnvVar = recipe.dirEnvVar;
+  const supplied = baseLookup(dirEnvVar)?.trim();
+  if (!supplied || !isAbsolute(supplied)) return baseLookup;
+  if ((await probePathKind(supplied, { pastCap: true })) === 'unknown') {
+    return (envVar: string) => (envVar === dirEnvVar ? undefined : baseLookup(envVar));
+  }
+  return baseLookup;
+}
+
 /**
  * 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
@@ -1641,7 +1671,8 @@ export function registerSessionRoutes(
       body.modelId,
       session.id,
       contextLength,
-      session.workingDir
+      session.workingDir,
+      await guardSessionConfigDirHome(entry, (envVar) => session.envOverrideValue(envVar))
     );
     if (!applied) {
       return createErrorResponse(ApiErrorCode.OPERATION_FAILED, `${session.mode} has no known custom-model mechanism`);
@@ -4528,7 +4559,8 @@ export function registerSessionRoutes(
         customModel.modelId,
         qsCustomModelSessionId,
         cmContextLength,
-        workspacePath
+        workspacePath,
+        await guardSessionConfigDirHome(cmEntry, (envVar) => qsGatedEnvOverrides?.[envVar])
       );
       if (!cmApplied) {
         return createErrorResponse(ApiErrorCode.OPERATION_FAILED, `${mode} has no known custom-model mechanism`);

src/web/server.ts

@@ -81,7 +81,12 @@ import { folderGrants } from '../folder-listing.js';
 import { getCli, enabledClis, listClis } from '../config/cli-registry/registry.js';
 import { isCliEntryInstalled, probeStockCliAvailability } from '../utils/cli-installed-probes.js';
 import { readCustomModelHosts, resolveCustomModelContextLength } from '../custom-model-hosts.js';
-import { applyCustomModelInjection, customModelConfigDir, removeConfigDir } from '../custom-model-injection-apply.js';
+import {
+  applyCustomModelInjection,
+  customModelConfigDir,
+  removeConfigDir,
+  type AppliedCustomModel,
+} from '../custom-model-injection-apply.js';
 import type { CustomModelBookkeeping } from '../types/session.js';
 import { registerGeneratedArtifactAttachment } from '../generated-artifact-attachments.js';
 import {
@@ -1454,7 +1459,7 @@ export class WebServer extends EventEmitter {
   private async _rebuildCustomModelEnv(
     session: Session,
     saved: CustomModelBookkeeping
-  ): Promise<Record<string, string> | undefined> {
+  ): Promise<AppliedCustomModel | undefined> {
     const entry = getCli(session.mode);
     if (!entry) return undefined;
     const endpoint = (await readCustomModelHosts(getDataDir())).find((h) => h.id === saved.endpointId);
@@ -1465,19 +1470,56 @@ export class WebServer extends EventEmitter {
       return undefined;
     }
     try {
+      // Boot recovery omits both `workingDir` (no reason to re-answer a trust dialog that
+      // already fired once) and the session-env real-home lookup: the injected VALUES are
+      // never persisted, so after a real restart the session can no longer carry its
+      // allowlisted `DSH_HOME` either (`getEnvOverridesForPersist()` keeps only
+      // `CLAUDE_CODE_*`/`CLAUDE_CONFIG_DIR`) — the lookup could only ever hit on the first
+      // apply in-process. Real-home resolution therefore falls back to the SERVER's
+      // `DSH_HOME` or the recipe's `realHomeFallback` (~/.dsh).
       return applyCustomModelInjection(
         entry,
         endpoint,
         saved.modelId,
         session.id,
         resolveCustomModelContextLength(endpoint, saved.modelId)
-      )?.envOverrides;
+      );
     } catch (err) {
       console.warn('[WebServer] Failed to rebuild custom-model env on recovery:', err);
       return undefined;
     }
   }
 
+  /**
+   * Restore one persisted custom-model selection (both boot-recovery paths). The rebuilt
+   * bookkeeping must come from the CURRENT recipe, not from the saved record: this is the
+   * first feature where a shipped recipe changed KIND (deepseek: env redirect -> per-session
+   * patch home), so a selection saved by an old build restores with e.g. no `configDir`
+   * while the new recipe writes one — and clearing it later could then never delete the
+   * generated dir. `envKeys` is the UNION of saved and applied keys: the tmux session may
+   * still carry `setenv`s from both, and a clear has to unset every one.
+   */
+  private async _restoreCustomModel(session: Session, saved: CustomModelBookkeeping): Promise<void> {
+    const applied = await this._rebuildCustomModelEnv(session, saved);
+    if (!applied) {
+      // Endpoint gone or CLI unregistered: restore the bookkeeping exactly as saved, which
+      // is what a later clear needs.
+      session.setCustomModel(saved);
+      return;
+    }
+    session.setCustomModel(
+      {
+        ...saved,
+        // Prefer the current recipe's dir; keep the saved one when the recipe writes none,
+        // so a clear can still delete a directory an older recipe created.
+        configDir: applied.configDir ?? saved.configDir,
+        launchModel: applied.launchModel,
+        envKeys: [...new Set([...saved.envKeys, ...applied.envKeys])],
+      },
+      applied.envOverrides
+    );
+  }
+
   /** Persists full session state including respawn config to state.json */
   private _persistSessionStateNow(session: Session): void {
     // See session-manager.updateSessionState: __envOverrides is an internal disk-only
@@ -3604,7 +3646,7 @@ export class WebServer extends EventEmitter {
       // bookkeeping survives a restart and the values are re-derived here.
       const savedCustomModel = (saved as { __customModel?: CustomModelBookkeeping }).__customModel;
       if (savedCustomModel) {
-        session.setCustomModel(savedCustomModel, await this._rebuildCustomModelEnv(session, savedCustomModel));
+        await this._restoreCustomModel(session, savedCustomModel);
       }
       if (saved.niceEnabled !== undefined || saved.niceValue !== undefined) {
         session.setNice({ enabled: saved.niceEnabled, niceValue: saved.niceValue });
@@ -3906,7 +3948,7 @@ export class WebServer extends EventEmitter {
             // the isolated config dir; an endpoint that has since been deleted still gets
             // the bookkeeping restored, which is what a later clear needs to unset.
             if (savedCustomModel) {
-              session.setCustomModel(savedCustomModel, await this._rebuildCustomModelEnv(session, savedCustomModel));
+              await this._restoreCustomModel(session, savedCustomModel);
             }
 
             // Update session name if it was a "Restored:" placeholder or doesn't match saved name