fix(custom-model): pass context limits and selected model to CLIs, add model picker filter and DeepSeek support

- opencode: write limit.context/output from the discovered context length (#749)
- codex: override the native launch model when a custom endpoint is selected (#750), and set model_context_window
- deepseek harness: add a deepseek-patch-json injection template
- model picker: add a search/filter box with a no-matches line

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>

src/config/cli-registry/schema.ts

@@ -580,7 +580,7 @@ const capabilitiesSchema = z
           kind: z.literal('configDir'),
           dirEnvVar: envName,
           fileName: z.string().min(1).max(80),
-          template: z.enum(['codex-toml', 'pi-models-json', 'omp-models-yml', 'grok-toml']),
+          template: z.enum(['codex-toml', 'pi-models-json', 'omp-models-yml', 'grok-toml', 'deepseek-patch-json']),
           launchModel: launchModelTemplate,
         })
         .strict(),

src/config/cli-registry/stock.ts

@@ -841,6 +841,7 @@ const CODEX: CliEntry = {
       dirEnvVar: 'CODEX_HOME',
       fileName: 'config.toml',
       template: 'codex-toml',
+      launchModel: '{modelId}',
     },
     // CODEX_HOME already matches the CODEX_ allowedPrefix above, so it was ALREADY
     // reachable via plain envOverrides before this feature existed. It is arguably
@@ -1547,28 +1548,12 @@ const DEEPSEEK: CliEntry = {
     // privilege rather than granting it, and clamping it here was a real regression
     // (test/deepseek-mode.test.ts) fixed before this shipped.
     privilegedEnvKeys: ['DSH_PERMISSION_MODE', 'DSH_HOME', 'DEEPSEEK_BASE_URL'],
-    // Reuses the already-existing DEEPSEEK_BASE_URL/DEEPSEEK_API_KEY keys above. No
-    // modelVars — dsh's model is a profile-composition entry (see `model: { source: 'none'
-    // }` above), not an env var, so forcing a specific model name may not fully work;
-    // verify against a real profile before shipping.
-    //
-    // ⚠️ appendV1Suffix is REQUIRED, not optional-nice-to-have: without it every request
-    // 404s. Confirmed live and by reading dsh's own bundled source
-    // (@deepseek-ai/dsh-llm-deepseek): it builds the request URL as
-    // `${DEEPSEEK_BASE_URL}/chat/completions` with no "/v1" of its own (its real public
-    // API, https://api.deepseek.com, expects the caller's base URL to already carry any
-    // needed prefix), while llama-swap/llama.cpp only serves the OpenAI-conventional
-    // "/v1/chat/completions" — a bare POST to ".../chat/completions" 404s live, and the
-    // 404 reported here originally ("dsh: HTTP_404: DeepSeek API error (HTTP 404)")
-    // matches dsh's own error-message template for exactly this failure. See the
-    // customModelInjection doc comment in cli-registry/types.ts for the full reasoning,
-    // including why claude/gemini must NOT get this.
+    // The installed profile supplies the transport; a per-session patch selects its exact model.
     customModelInjection: {
-      kind: 'env',
-      baseUrlVar: 'DEEPSEEK_BASE_URL',
-      apiKeyVar: 'DEEPSEEK_API_KEY',
-      modelVars: [],
-      appendV1Suffix: true,
+      kind: 'configDir',
+      dirEnvVar: 'DSH_HOME',
+      fileName: 'cordis.patch.yml',
+      template: 'deepseek-patch-json',
     },
   },
   overlays: {

src/config/cli-registry/types.ts

@@ -888,7 +888,7 @@ export interface CliCapabilities {
         kind: 'configDir';
         dirEnvVar: string;
         fileName: string;
-        template: 'codex-toml' | 'pi-models-json' | 'omp-models-yml' | 'grok-toml';
+        template: 'codex-toml' | 'pi-models-json' | 'omp-models-yml' | 'grok-toml' | 'deepseek-patch-json';
         launchModel?: string;
       }
     | { kind: 'unsupported' };

src/custom-model-injection-apply.ts

@@ -46,6 +46,14 @@ export function applyConfigDirInjection(baseDir: string, injection: ConfigDirInj
     writeFileSync(filePath, file.content, { encoding: 'utf8', mode: 0o600 });
     chmodSync(filePath, 0o600);
   }
+  if (injection.dirEnvVar === 'DSH_HOME') {
+    // Reuse installed profile bundles without changing the user's profile or credentials.
+    const profiles = join(baseDir, 'profiles');
+    if (!existsSync(profiles)) {
+      const realHome = process.env.DSH_HOME?.trim() || join(homedir(), '.dsh');
+      symlinkSync(join(realHome, 'profiles'), profiles, platform() === 'win32' ? 'junction' : 'dir');
+    }
+  }
   return { [injection.dirEnvVar]: baseDir, ...injection.extraEnv };
 }
 
@@ -284,5 +292,6 @@ export function applyCustomModelInjection(
   }
   const configDir = customModelConfigDir(sessionId);
   const envOverrides = applyConfigDirInjection(configDir, injection);
+
   return { envOverrides, envKeys: Object.keys(envOverrides), configDir, launchModel: injection.launchModel };
 }

src/custom-model-injection.ts

@@ -136,12 +136,12 @@ export function buildCustomModelInjection(
     }
 
     case 'configContentEnv': {
-      const content = renderConfigContent(cap.template, endpoint, modelId, apiKey);
+      const content = renderConfigContent(cap.template, endpoint, modelId, apiKey, contextLength);
       return withLaunchModel({ kind: 'env', envOverrides: { [cap.envVar]: content } }, cap.launchModel, modelId);
     }
 
     case 'configDir': {
-      const { content, extraEnv } = renderConfigFile(cap.template, endpoint, modelId, apiKey);
+      const { content, extraEnv } = renderConfigFile(cap.template, endpoint, modelId, apiKey, contextLength);
       return withLaunchModel(
         { kind: 'configDir', dirEnvVar: cap.dirEnvVar, files: [{ relPath: cap.fileName, content }], extraEnv },
         cap.launchModel,
@@ -164,24 +164,47 @@ function withLaunchModel<T extends EnvInjection | ConfigDirInjection>(
   return { ...result, launchModel: template.split('{modelId}').join(modelId) };
 }
 
+/**
+ * One quarter of the window is held back for the reply, capped at 8192 tokens (a small local
+ * model's window must not lose a disproportionate slice to the reservation). Returns undefined
+ * for an unknown or non-finite size — opencode then keeps its own default guess, which is the
+ * pre-fix behaviour; never invent a limit here.
+ */
+function opencodeModelLimit(contextLength: number | undefined): { context: number; output: number } | undefined {
+  if (contextLength === undefined || !Number.isFinite(contextLength)) return undefined;
+  const total = Math.trunc(contextLength);
+  if (total <= 0) return undefined;
+  const output = Math.max(1, Math.min(8192, Math.floor(total / 4)));
+  return { context: total - output, output };
+}
+
 function renderConfigContent(
   template: 'opencode-json',
   endpoint: CustomModelEndpoint,
   modelId: string,
-  apiKey: string
+  apiKey: string,
+  contextLength?: number
 ): string {
   switch (template) {
-    case 'opencode-json':
+    case 'opencode-json': {
+      // `limit` carries the discovered context window (issue #749): without it opencode assumes
+      // a large default window for an unrecognized model id and eventually overflows a much
+      // smaller local server. `context` is what opencode caps the PROMPT at, so the response
+      // headroom from `opencodeModelLimit` is subtracted up front — `output` is opencode's own
+      // cap on the reply, so setting them from the same discovered total keeps a single turn
+      // inside the real window.
+      const limit = opencodeModelLimit(contextLength);
       return JSON.stringify({
         $schema: 'https://opencode.ai/config.json',
         provider: {
           custom: {
             options: { baseURL: withV1Suffix(endpoint.baseUrl), apiKey },
-            models: { [modelId]: {} },
+            models: { [modelId]: limit ? { limit } : {} },
           },
         },
         model: `custom/${modelId}`,
       });
+    }
   }
 }
 
@@ -192,13 +215,53 @@ const CODEX_API_KEY_ENV_VAR = 'CODEMAN_CUSTOM_MODEL_API_KEY';
 export const GROK_CUSTOM_MODEL_NAME = 'codeman-custom';
 
 function renderConfigFile(
-  template: 'codex-toml' | 'pi-models-json' | 'omp-models-yml' | 'grok-toml',
+  template: 'codex-toml' | 'pi-models-json' | 'omp-models-yml' | 'grok-toml' | 'deepseek-patch-json',
   endpoint: CustomModelEndpoint,
   modelId: string,
-  apiKey: string
+  apiKey: string,
+  contextLength?: number
 ): { content: string; extraEnv?: Record<string, string> } {
   const baseUrl = withV1Suffix(endpoint.baseUrl);
   switch (template) {
+    case 'deepseek-patch-json': {
+      const route = { provider: 'codeman-custom', model: modelId };
+      return {
+        content: JSON.stringify(
+          [
+            {
+              id: 'llm-pi-ai',
+              name: '@deepseek-ai/dsh-llm-pi-ai',
+              config: {
+                providers: {
+                  'codeman-custom': {
+                    apiKeyEnv: 'DEEPSEEK_API_KEY',
+                    api: 'openai-completions',
+                    baseURL: baseUrl,
+                    models: [
+                      {
+                        id: modelId,
+                        name: modelId,
+                        ...(contextLength !== undefined && Number.isFinite(contextLength) && contextLength > 0
+                          ? {
+                              contextWindow: Math.trunc(contextLength),
+                              maxTokens: Math.max(1, Math.min(8192, Math.floor(contextLength / 4))),
+                            }
+                          : {}),
+                      },
+                    ],
+                  },
+                },
+              },
+            },
+            { id: 'dsh-tui', name: '@deepseek-harness-tui/dsh-tui', config: route },
+            { id: 'agent-default-model', name: '@deepseek-ai/dsh-agent-default-model', config: route },
+          ],
+          null,
+          2
+        ),
+        extraEnv: { DEEPSEEK_API_KEY: apiKey },
+      };
+    }
     case 'codex-toml': {
       // Verified against real codex (>= Feb 2026): `model` is a top-level STRING, never
       // a `[model].default` table — codex rejects that with "invalid type: map, expected
@@ -217,6 +280,12 @@ function renderConfigFile(
       const content = [
         `model = ${quoted(modelId)}`,
         `model_provider = "custom"`,
+        ...(contextLength !== undefined && Number.isFinite(contextLength) && contextLength > 0
+          ? [
+              `model_context_window = ${Math.trunc(contextLength)}`,
+              `model_auto_compact_token_limit = ${Math.max(1, Math.floor(contextLength * 0.75))}`,
+            ]
+          : []),
         '',
         '[model_providers.custom]',
         `name = "Custom Endpoint"`,

src/web/public/index.html

@@ -1033,6 +1033,14 @@
         </div>
         <div class="modal-body">
           <p class="form-hint" id="customModelPickHint"></p>
+          <!-- Case-insensitive filter over the rendered rows (app.filterCustomModelPick):
+               a display layer only, the rows themselves are never re-rendered. Reset and
+               focused on every open, same in-memory rule as the rail's search box. -->
+          <input type="search" id="customModelPickSearch" class="session-sidebar-filter-input custom-model-pick-search"
+            placeholder="Search models" aria-label="Search models"
+            autocomplete="off" autocapitalize="off" spellcheck="false" enterkeyhint="search"
+            oninput="app.filterCustomModelPick(this.value)">
+          <p class="form-hint custom-model-pick-no-matches" id="customModelPickNoMatches" role="status" hidden>No models match</p>
           <div id="customModelPickList" class="run-mode-custom-models"></div>
         </div>
       </div>

src/web/public/session-ui.js

@@ -1088,13 +1088,53 @@ Object.assign(CodemanApp.prototype, {
         const promotion = m === currentlyLoaded ? 'Currently loaded' : m === lastUsed ? 'Last used' : null;
         const tags = [promotion, m === host.defaultModelId ? 'Default' : null].filter(Boolean);
         const arg = escapeHtml(JSON.stringify(m));
+        // data-model-id is the filter's haystack (escapeHtml covers `"` as well as
+        // `<>&`, so a hostile model id cannot break out of the attribute); the
+        // filter reads it back through dataset, which decodes it.
         return `
-          <button class="run-mode-option" onclick="app.chooseCustomModelAndRun(${arg})">
+          <button class="run-mode-option" data-model-id="${escapeHtml(m)}" onclick="app.chooseCustomModelAndRun(${arg})">
             <span class="run-mode-dot ${escapeHtml(mode)}"></span>${escapeHtml(m)}${tags.map((t) => ` <span class="set-scope">${escapeHtml(t)}</span>`).join('')}
           </button>`;
       })
       .join('');
     modal.classList.add('active');
+    // A fresh open always starts unfiltered with the caret in the search box — the
+    // list was just rebuilt, so clearing the input is the whole reset; focus is the
+    // user's next keystroke away. Inside the generation guard above, so a
+    // superseded probe can neither focus nor clear a modal that now shows another
+    // endpoint's models.
+    const search = document.getElementById('customModelPickSearch');
+    if (search) {
+      search.value = '';
+      search.focus();
+    }
+    this.filterCustomModelPick('');
+  },
+
+  /**
+   * View filter for the open "Choose a model" picker: case-insensitive substring
+   * over each row's model id, driven from the search input's own `oninput`.
+   * Deliberately toggles `hidden` on the already-rendered buttons rather than
+   * re-rendering from a second copy of the model list: the loaded/last-used
+   * promotion, the Default pill, the escaped inline click argument and the async
+   * generation guard all then stay exactly where they are, and clearing the
+   * query restores the list byte for byte. ⚠️ `.run-mode-option` carries its own
+   * `display: flex` (styles.css, restated in mobile.css), which outranks the UA
+   * `[hidden]` rule, so styles.css re-asserts `display: none !important` for
+   * these rows — without it the filter would silently do nothing.
+   */
+  filterCustomModelPick(value) {
+    const list = document.getElementById('customModelPickList');
+    if (!list) return;
+    const query = String(value || '').trim().toLowerCase();
+    let visible = 0;
+    for (const btn of list.querySelectorAll('button[data-model-id]')) {
+      const match = !query || btn.dataset.modelId.toLowerCase().includes(query);
+      btn.hidden = !match;
+      if (match) visible += 1;
+    }
+    const noMatches = document.getElementById('customModelPickNoMatches');
+    if (noMatches) noMatches.hidden = visible > 0;
   },
 
   closeCustomModelPickModal() {

src/web/public/styles.css

@@ -7807,6 +7807,27 @@ html[data-skin="og"] .welcome-primary:hover {
   opacity: 0.8;
 }
 
+/* The picker's search box reuses .session-sidebar-filter-input's theme-token
+   styling (same reasoning as the .set-scope pill above) — only its own spacing
+   and the no-matches line are added here. */
+#customModelPickModal .custom-model-pick-search {
+  margin-bottom: 0.5rem;
+}
+
+#customModelPickModal .custom-model-pick-no-matches {
+  text-align: center;
+  padding: 1rem 0;
+}
+
+/* A filtered-out row's `hidden` must actually hide it: `.run-mode-option` sets
+   `display: flex` (and mobile.css restates the class in a media query), which
+   outranks the UA `[hidden] { display: none }` rule, so the filter would
+   silently do nothing without this re-assertion. Scoped to this modal's rows;
+   the Run menu's own .run-mode-option entries never take `hidden`. */
+#customModelPickModal .run-mode-option[hidden] {
+  display: none !important;
+}
+
 /* Custom Model Endpoint Profiles: llama-swap model-swap confirmation — replaces a native
    confirm() popup (docs/custom-model-endpoints-plan.md) so it looks and feels like the
    rest of the app instead of a browser chrome dialog. Shares the context-window-too-small

test/Deepseek-CustomEndpoint.test.ts

@@ -0,0 +1,64 @@
+import { mkdirSync, readFileSync, realpathSync, writeFileSync } from 'node:fs';
+import { homedir } from 'node:os';
+import { join } from 'node:path';
+import { afterEach, describe, expect, it, vi } from 'vitest';
+import { getCli } from '../src/config/cli-registry/index.js';
+import { buildCustomModelInjection } from '../src/custom-model-injection.js';
+import {
+  applyCustomModelInjection,
+  removeConfigDir,
+  customModelConfigDir,
+} from '../src/custom-model-injection-apply.js';
+
+afterEach(() => {
+  removeConfigDir(customModelConfigDir('deepseek-probe'));
+  vi.unstubAllEnvs();
+});
+
+describe('DeepSeek custom endpoint isolation', () => {
+  it('uses the chosen model and limits without changing installed profiles or embedding the key', () => {
+    const realHome = join(homedir(), '.dsh');
+    const profile = join(realHome, 'profiles', 'dsh-tui');
+    mkdirSync(profile, { recursive: true });
+    const original = join(profile, 'cordis.patch.yml');
+    writeFileSync(original, 'original profile');
+    vi.stubEnv('DSH_HOME', realHome);
+    const entry = getCli('deepseek');
+    if (!entry) throw new Error('Missing DeepSeek entry');
+    const endpoint = { id: 'local', label: 'Local', baseUrl: 'http://box:8080', apiKey: 'private-probe-key' };
+    const applied = applyCustomModelInjection(entry, endpoint, 'chosen-model', 'deepseek-probe', 131072);
+    if (!applied?.configDir) throw new Error('Missing isolated profile');
+    const content = readFileSync(join(applied.configDir, 'cordis.patch.yml'), 'utf8');
+    expect(content).not.toContain(endpoint.apiKey);
+    expect(applied.envOverrides.DEEPSEEK_API_KEY).toBe(endpoint.apiKey);
+    const patch = JSON.parse(content);
+    const provider = patch.find((row: { id: string }) => row.id === 'llm-pi-ai').config.providers['codeman-custom'];
+    expect(provider.api).toBe('openai-completions');
+    expect(provider.baseURL).toBe('http://box:8080/v1');
+    expect(provider.models).toEqual([
+      { id: 'chosen-model', name: 'chosen-model', contextWindow: 131072, maxTokens: 8192 },
+    ]);
+    expect(patch.find((row: { id: string }) => row.id === 'dsh-tui').config).toEqual({
+      provider: 'codeman-custom',
+      model: 'chosen-model',
+    });
+    expect(realpathSync(join(applied.configDir, 'profiles'))).toBe(join(realHome, 'profiles'));
+    removeConfigDir(applied.configDir);
+    expect(readFileSync(original, 'utf8')).toBe('original profile');
+  });
+
+  it('gives Codex its known context and compaction budget', () => {
+    const entry = getCli('codex');
+    if (!entry) throw new Error('Missing Codex entry');
+    const injection = buildCustomModelInjection(
+      entry,
+      { id: 'local', label: 'Local', baseUrl: 'http://box' },
+      'chosen-model',
+      131072
+    );
+    if (injection.kind !== 'configDir') throw new Error('Expected isolated Codex config');
+    expect(injection.files[0].content).toContain('model_context_window = 131072');
+    expect(injection.files[0].content).toContain('model_auto_compact_token_limit = 98304');
+    expect(injection.launchModel).toBe('chosen-model');
+  });
+});

test/custom-model-injection-apply.test.ts

@@ -53,9 +53,12 @@ describe('applyCustomModelInjection: context length', () => {
     expect(applied?.envOverrides.CLAUDE_CODE_MAX_CONTEXT_TOKENS).toBeUndefined();
   });
 
-  it('deepseek: has no contextLengthVar declared, so a passed-in length is a no-op', () => {
-    const applied = applyCustomModelInjection(entryOrThrow('deepseek'), endpoint, 'qwen3', 'sess-ctx-3', 16384);
-    expect(Object.keys(applied?.envOverrides ?? {}).sort()).toEqual(['DEEPSEEK_API_KEY', 'DEEPSEEK_BASE_URL']);
+  it('deepseek: passes the known context through its isolated model catalogue', () => {
+    const sessionId = 'sess-deepseek-context';
+    sessionsToClean.push(sessionId);
+    const applied = applyCustomModelInjection(entryOrThrow('deepseek'), endpoint, 'qwen3', sessionId, 32768);
+    expect(Object.keys(applied?.envOverrides ?? {}).sort()).toEqual(['DEEPSEEK_API_KEY', 'DSH_HOME']);
+    expect(readFileSync(join(applied!.configDir!, 'cordis.patch.yml'), 'utf8')).toContain('"contextWindow": 32768');
   });
 });
 
@@ -103,11 +106,12 @@ describe('applyCustomModelInjection: CLAUDE_CONFIG_DIR isolation', () => {
     expect(applied?.envOverrides.HOME).toBe(customModelConfigDir(sessionId));
   });
 
-  it('deepseek: no configDirVar declared, so no config dir is created at all', () => {
+  it('deepseek: creates an isolated profile patch', () => {
     const sessionId = 'sess-cfgdir-deepseek';
+    sessionsToClean.push(sessionId);
     const applied = applyCustomModelInjection(entryOrThrow('deepseek'), endpoint, 'qwen3', sessionId);
-    expect(applied?.configDir).toBeUndefined();
-    expect(existsSync(customModelConfigDir(sessionId))).toBe(false);
+    expect(applied?.configDir).toBe(customModelConfigDir(sessionId));
+    expect(existsSync(join(applied!.configDir!, 'cordis.patch.yml'))).toBe(true);
   });
 });
 

test/custom-model-injection.test.ts

@@ -112,6 +112,31 @@ describe('buildCustomModelInjection', () => {
     expect(parsed.provider.custom.models.qwen3).toEqual({});
   });
 
+  it('opencode: threads a discovered context length into the model limit with response headroom (issue #749)', () => {
+    const result = buildCustomModelInjection(entryOrThrow('opencode'), endpoint, 'qwen3', 16384);
+    if (result.kind !== 'env') throw new Error('unreachable');
+    const parsed = JSON.parse(result.envOverrides.OPENCODE_CONFIG_CONTENT);
+    // One quarter held back for the reply: context 16384-4096, output 4096 — the sum is the
+    // real window, so a full-size prompt plus a max-length reply never exceeds the server.
+    expect(parsed.provider.custom.models.qwen3).toEqual({ limit: { context: 12288, output: 4096 } });
+  });
+
+  it('opencode: caps the response headroom reservation at 8192 for big windows', () => {
+    const result = buildCustomModelInjection(entryOrThrow('opencode'), endpoint, 'qwen3', 262144);
+    if (result.kind !== 'env') throw new Error('unreachable');
+    const parsed = JSON.parse(result.envOverrides.OPENCODE_CONFIG_CONTENT);
+    expect(parsed.provider.custom.models.qwen3).toEqual({ limit: { context: 253952, output: 8192 } });
+  });
+
+  it('opencode: never invents a limit for an unknown or non-finite context length (issue #749 regression)', () => {
+    for (const contextLength of [undefined, NaN]) {
+      const result = buildCustomModelInjection(entryOrThrow('opencode'), endpoint, 'qwen3', contextLength);
+      if (result.kind !== 'env') throw new Error('unreachable');
+      const parsed = JSON.parse(result.envOverrides.OPENCODE_CONFIG_CONTENT);
+      expect(parsed.provider.custom.models.qwen3).toEqual({});
+    }
+  });
+
   it('codex: configDir writes an isolated config.toml with model/base_url, and the key rides as extraEnv (never a literal TOML field)', () => {
     const result = buildCustomModelInjection(entryOrThrow('codex'), endpoint, 'qwen3');
     expect(result.kind).toBe('configDir');
@@ -179,29 +204,25 @@ describe('buildCustomModelInjection', () => {
     expect(result.extraEnv).toEqual({ XAI_API_KEY: 'my-key' });
   });
 
-  it('deepseek: env kind sets base URL (with a /v1 suffix appended) and key, no model var', () => {
-    // appendV1Suffix is REQUIRED here, not cosmetic: confirmed by reading dsh's own
-    // bundled source (@deepseek-ai/dsh-llm-deepseek) that it builds the request URL as
-    // `${DEEPSEEK_BASE_URL}/chat/completions` with no "/v1" of its own, while
-    // llama-swap/llama.cpp only serves "/v1/chat/completions" — without this, every
-    // request 404s (confirmed live; this is the fix for the originally-reported
-    // "dsh: HTTP_404: DeepSeek API error (HTTP 404)").
+  it('deepseek: isolates the selected model route and passes its key by reference', () => {
     const result = buildCustomModelInjection(entryOrThrow('deepseek'), endpoint, 'qwen3');
-    if (result.kind !== 'env') throw new Error('unreachable');
-    expect(result.envOverrides).toEqual({
-      DEEPSEEK_BASE_URL: 'http://192.168.1.50:8080/v1',
-      DEEPSEEK_API_KEY: 'my-key',
-    });
+    if (result.kind !== 'configDir') throw new Error('Expected isolated DeepSeek config');
+    expect(result.dirEnvVar).toBe('DSH_HOME');
+    expect(result.extraEnv).toEqual({ DEEPSEEK_API_KEY: 'my-key' });
+    expect(result.files[0].content).not.toContain('my-key');
+    const patch = JSON.parse(result.files[0].content);
+    expect(patch.find((row: { id: string }) => row.id === 'dsh-tui').config.model).toBe('qwen3');
   });
 
-  it('deepseek: appending the /v1 suffix is idempotent against a baseUrl that already ends in /v1', () => {
+  it('deepseek: preserves an existing version suffix', () => {
     const result = buildCustomModelInjection(
       entryOrThrow('deepseek'),
-      { ...endpoint, baseUrl: 'http://192.168.1.50:8080/v1' },
+      { ...endpoint, baseUrl: endpoint.baseUrl + '/v1' },
       'qwen3'
     );
-    if (result.kind !== 'env') throw new Error('unreachable');
-    expect(result.envOverrides.DEEPSEEK_BASE_URL).toBe('http://192.168.1.50:8080/v1');
+    if (result.kind !== 'configDir') throw new Error('Expected isolated DeepSeek config');
+    expect(result.files[0].content).toContain('http://192.168.1.50:8080/v1');
+    expect(result.files[0].content).not.toContain('/v1/v1');
   });
 
   it('antigravity: unsupported', () => {
@@ -232,7 +253,9 @@ describe('launchModel (the model launch param that selects the injected provider
   });
 
   it('CLIs whose config selects the model on its own declare none', () => {
-    for (const id of ['claude', 'opencode', 'codex', 'gemini', 'deepseek']) {
+    // codex now declares launchModel (selected-model launch override) and is covered by
+    // its own restart coverage, not here.
+    for (const id of ['claude', 'opencode', 'gemini', 'deepseek']) {
       const result = buildCustomModelInjection(entryOrThrow(id), endpoint, 'qwen3');
       if (result.kind === 'unsupported') throw new Error('unreachable');
       expect(result.launchModel, id).toBeUndefined();

test/custom-model-run-menu-ui.test.ts

@@ -20,6 +20,10 @@ import { describe, expect, it, vi } from 'vitest';
 
 const CONSTANTS_JS = readFileSync(new URL('../src/web/public/constants.js', import.meta.url), 'utf-8');
 const SESSION_UI_JS = readFileSync(new URL('../src/web/public/session-ui.js', import.meta.url), 'utf-8');
+// Only for the [hidden] CSS guard below — the filter toggles the `hidden` property, and
+// `.run-mode-option`'s own `display: flex` would silently defeat it without the
+// `!important` re-assertion in styles.css.
+const STYLES_CSS = readFileSync(new URL('../src/web/public/styles.css', import.meta.url), 'utf-8');
 // Only for the real _showCenterStatus DOM tests below (`bootAppWithRealCenterStatus`) —
 // every other test in this file stubs _showCenterStatus itself and has no need of it.
 const PANELS_UI_JS = readFileSync(new URL('../src/web/public/panels-ui.js', import.meta.url), 'utf-8');
@@ -55,6 +59,9 @@ function bootApp(
       <div class="modal" id="customModelPickModal">
         <h3 id="customModelPickTitle"></h3>
         <p id="customModelPickHint"></p>
+        <input type="search" id="customModelPickSearch" aria-label="Search models"
+          oninput="app.filterCustomModelPick(this.value)">
+        <p id="customModelPickNoMatches" role="status" hidden>No models match</p>
         <div id="customModelPickList"></div>
       </div>
       <div class="modal" id="customModelSwapConfirmModal">
@@ -532,6 +539,121 @@ describe('Custom Model Endpoint Profiles: the "which model" picker', () => {
     await app.selectCustomModelEntry('claude', 'llama-box');
     expect(toastMessage).toMatch(/no models discovered/i);
   });
+
+  it('resets and focuses the search box every time the picker opens', async () => {
+    const { win, app } = bootApp({
+      hosts: [{ id: 'llama-box', label: 'llama.cpp', baseUrl: 'http://x', models: ['qwen3', 'llama3'] }],
+    });
+    win.app = app;
+    await app.selectCustomModelEntry('claude', 'llama-box');
+    const search = win.document.getElementById('customModelPickSearch') as HTMLInputElement;
+    // The caret lands in the box, so the first keystroke filters with no click.
+    expect(win.document.activeElement).toBe(search);
+    // A stale query from a previous open must not survive into the next one.
+    search.value = 'zzz';
+    search.dispatchEvent(new win.Event('input'));
+    app.closeCustomModelPickModal();
+
+    await app.selectCustomModelEntry('claude', 'llama-box');
+    expect(search.value).toBe('');
+    expect(win.document.activeElement).toBe(search);
+    expect(win.document.getElementById('customModelPickNoMatches')!.hasAttribute('hidden')).toBe(true);
+    const visible = [...win.document.getElementById('customModelPickList')!.querySelectorAll('button')].filter(
+      (b) => !b.hasAttribute('hidden')
+    );
+    expect(visible).toHaveLength(2);
+  });
+
+  it('filters rows case-insensitively on the model id, keeping the surviving row fully functional', async () => {
+    const { win, app } = bootApp({
+      hosts: [
+        {
+          id: 'llama-box',
+          label: 'llama.cpp',
+          baseUrl: 'http://x',
+          models: ['qwen3', 'llama3'],
+          defaultModelId: 'qwen3',
+        },
+      ],
+    });
+    let launched: unknown[] | null = null;
+    app.runCustomModelEntry = async (...args: unknown[]) => {
+      launched = args;
+    };
+    win.app = app;
+    await app.selectCustomModelEntry('claude', 'llama-box');
+    const search = win.document.getElementById('customModelPickSearch') as HTMLInputElement;
+    search.value = 'QWEN';
+    search.dispatchEvent(new win.Event('input'));
+
+    const buttons = [...win.document.getElementById('customModelPickList')!.querySelectorAll('button')];
+    expect(buttons.filter((b) => b.hasAttribute('hidden')).map((b) => b.textContent!.trim())).toEqual(['llama3']);
+    const [visible] = buttons.filter((b) => !b.hasAttribute('hidden'));
+    // The surviving row keeps its Default badge and its real, callable click handler.
+    expect(visible.textContent).toContain('qwen3');
+    expect(visible.textContent).toContain('Default');
+    (visible as unknown as HTMLButtonElement & { onclick: (e: unknown) => void }).onclick(
+      new (win as any).Event('click')
+    );
+    expect(launched).toEqual(['claude', 'llama-box', 'qwen3']);
+  });
+
+  it('shows the no-matches line only while a query matches nothing, and clears it with the query', async () => {
+    const { win, app } = bootApp({
+      hosts: [{ id: 'llama-box', label: 'llama.cpp', baseUrl: 'http://x', models: ['qwen3', 'llama3'] }],
+    });
+    win.app = app;
+    await app.selectCustomModelEntry('claude', 'llama-box');
+    const search = win.document.getElementById('customModelPickSearch') as HTMLInputElement;
+    const noMatches = win.document.getElementById('customModelPickNoMatches')!;
+    const isHidden = () =>
+      win.document.getElementById('customModelPickList')!.querySelectorAll('button[hidden]').length;
+
+    // Whitespace is not a query: everything stays visible, no message.
+    search.value = '   ';
+    search.dispatchEvent(new win.Event('input'));
+    expect(noMatches.hasAttribute('hidden')).toBe(true);
+    expect(isHidden()).toBe(0);
+
+    search.value = 'ghost';
+    search.dispatchEvent(new win.Event('input'));
+    expect(noMatches.hasAttribute('hidden')).toBe(false);
+    expect(isHidden()).toBe(2);
+
+    search.value = '';
+    search.dispatchEvent(new win.Event('input'));
+    expect(noMatches.hasAttribute('hidden')).toBe(true);
+    expect(isHidden()).toBe(0);
+  });
+
+  it('keeps an HTML-significant model id inert in the picker rows too, and filterable by its raw text', async () => {
+    // Same vector as the Run-menu row above, now via data-model-id: escapeHtml covers
+    // the double quote, and the filter reads the decoded raw id back off dataset.
+    const dangerousModel = '"><img src=x onerror=alert(1)>';
+    const { win, app } = bootApp({
+      hosts: [{ id: 'llama-box', label: 'llama.cpp', baseUrl: 'http://x', models: ['qwen3', dangerousModel] }],
+    });
+    win.app = app;
+    await app.selectCustomModelEntry('claude', 'llama-box');
+    const list = win.document.getElementById('customModelPickList')!;
+    expect(list.querySelector('img')).toBeNull();
+
+    const search = win.document.getElementById('customModelPickSearch') as HTMLInputElement;
+    search.value = 'src=x';
+    search.dispatchEvent(new win.Event('input'));
+    const visible = list.querySelectorAll('button:not([hidden])');
+    expect(visible).toHaveLength(1);
+    expect(visible[0].getAttribute('data-model-id')).toBe(dangerousModel);
+  });
+
+  it('re-asserts display:none !important for hidden picker rows so the filter cannot be silently defeated', () => {
+    // `.run-mode-option` carries its own `display: flex` (styles.css, restated in
+    // mobile.css), which outranks the UA `[hidden]` rule — without this scoped
+    // !important re-assertion, toggling `hidden` would change nothing on screen.
+    const rule = STYLES_CSS.match(/#customModelPickModal \.run-mode-option\[hidden\]\s*\{[^}]*\}/);
+    expect(rule, 'picker rows need a [hidden] rule scoped to #customModelPickModal').toBeTruthy();
+    expect(rule![0]).toMatch(/display:\s*none\s*!important/);
+  });
 });
 
 describe('Custom Model Endpoint Profiles: _getCustomModelCurrentlyLoaded is client-side bounded', () => {

test/session-custom-model-restart.test.ts

@@ -27,6 +27,8 @@ import { join } from 'node:path';
 import { afterEach, describe, expect, it, vi } from 'vitest';
 
 import { Session } from '../src/session.js';
+import { getCli } from '../src/config/cli-registry/index.js';
+import { buildCustomModelInjection } from '../src/custom-model-injection.js';
 import { TmuxManager } from '../src/tmux-manager.js';
 import type { MuxSession, SessionMode } from '../src/types.js';
 
@@ -225,3 +227,29 @@ describe('launchModel reaches the CLI through its own launch param', () => {
     expect(respawn.mock.calls[0][0].model).toBeUndefined();
   });
 });
+
+describe('Codex custom endpoint model overrides', () => {
+  it('selects the local model over a native launch default and restores the default on clear', async () => {
+    const entry = getCli('codex');
+    if (!entry) throw new Error('Missing Codex entry');
+    const injection = buildCustomModelInjection(
+      entry,
+      { id: 'ep', label: 'Local', baseUrl: 'http://box:8080' },
+      'qwen3'
+    );
+    if (injection.kind !== 'configDir') throw new Error('Expected isolated Codex config');
+    const { session, respawn } = liveSession('codex', {
+      codexConfig: { model: 'native-model', reasoningEffort: 'high' },
+    });
+    session.setCustomModel(
+      { endpointId: 'ep', modelId: 'qwen3', envKeys: ['CODEX_HOME'], launchModel: injection.launchModel },
+      { CODEX_HOME: '/isolated/codex' }
+    );
+    await session.restartCli();
+    expect(respawn.mock.calls[0][0].codexConfig).toEqual({ model: 'qwen3', reasoningEffort: 'high' });
+    session.setCustomModel(undefined);
+    respawn.mockClear();
+    await session.restartCli();
+    expect(respawn.mock.calls[0][0].codexConfig).toEqual({ model: 'native-model', reasoningEffort: 'high' });
+  });
+});