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

- 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
- model picker: add a search/filter box with a no-matches line

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