fix(custom-model): show which model a session is using when an endpoint cannot report it

Only llama-swap answers what is loaded, so behind a gateway such as Bifrost
nothing was marked and the picker fell back to discovery order apart from the
one CLI that had launched there before. A live session whose own injected
endpoint is that host now promotes its model as "In use by a session", under
its own tag and below llama-swap's "Currently loaded" answer, reading only
what Codeman injected rather than terminal text, and never a stopped session.
When genuinely nothing is known the picker says so instead of leaving an
unmarked wall, and stays quiet for an endpoint that merely failed to answer.

.changeset/custom-model-picker-in-use.md

@@ -0,0 +1,5 @@
+---
+'aicodeman': patch
+---
+
+The "Choose a model" picker now says which model is actually in use on an endpoint that cannot report it. Only llama-swap answers that question, so behind a gateway such as Bifrost (and behind a bare llama.cpp, Ollama or vLLM) nothing was marked and the list fell back to plain discovery order, apart from the one CLI that happened to have launched there before. A live session whose own injected endpoint is that host now promotes its model as **"In use by a session"**, under its own tag and behind llama-swap's own "Currently loaded" answer, reading only what Codeman injected rather than text scraped off a terminal, and never a stopped session. When genuinely nothing is known the picker says so instead of leaving an unmarked wall, and it stays quiet for an endpoint that merely failed to answer. Pinned by test/custom-model-run-menu-ui.test.ts.

docs/custom-model-endpoints.md

@@ -200,32 +200,62 @@ saved default, not just confirming it.
 
 The modal promotes exactly one row to the top of the list rather than
 always showing raw discovery order, so the zero-wait choice is the one
-under your thumb:
+under your thumb. Three kinds of knowledge feed that promotion, best
+evidence first, and the first one that answers wins:
 
-- **"Currently loaded"** — a model from this host's own list that
+- **"Currently loaded"** is a model from this host's own list that
   llama-swap reports `ready` right now, queried via
   `GET /api/model-endpoints/:id/running-status`. Bounded client-side to
   ~800ms (`Promise.race`), on top of the route's own 5s server-side
   timeout, so an endpoint that is asleep or firewalled cannot leave the
   modal invisible for the full 5s after the Run menu has already closed.
-- **"Last used"** — shown only when nothing is currently loaded: the model
-  actually launched last for this exact (harness, endpoint) pair, read
-  from the per-device `codeman:customModelLastUsed:<mode>:<endpointId>`
-  localStorage key. Written by `_runCustomModelEntryViaRestart` (claude)
-  and `_quickStartWithCustomModelConfirm` (every one-shot launch; the
+- **"In use by a session"** is the fallback for every endpoint that
+  cannot report its own loaded model, which is every server except
+  llama-swap: a bare llama.cpp, Ollama, vLLM, and a gateway such as
+  Bifrost fronting a whole fleet all answer `isLlamaSwap: false`.
+  `_getCustomModelInUseBySession` walks `this.sessions` for a session of
+  this very instance whose `customModel.endpointId` is this host, newest
+  `createdAt` wins, and promotes its model. A live session is first-hand
+  evidence of a model in use on the endpoint, because Codeman put it
+  there, so it earns the promotion and the tag says where the knowledge
+  came from. Two fences keep it honest: it reads only `customModel`,
+  never `displayModel` (display text scraped off a CLI footer, so a
+  terminal that merely printed a similar string must not mark a row),
+  and a session with `status: 'stopped'` or a recorded `paneExit` does
+  not count, since nothing is on the endpoint any more. Sessions on other
+  endpoints, and models the host no longer discovers, are skipped.
+- **"Last used"** appears only when neither of the above answers: the
+  model actually launched last for this exact (harness, endpoint) pair,
+  read from the per-device localStorage key
+  `codeman:customModelLastUsed:<mode>:<endpointId>`. That key is per CLI
+  on purpose, so it can only
+  ever promote the CLI that launched there before, which is why a gateway
+  box with no session running shows plain discovery order for the other
+  CLIs. Written by `_runCustomModelEntryViaRestart` (claude) and
+  `_quickStartWithCustomModelConfirm` (every one-shot launch; the
   `runCustomModelEntry` entry point itself only dispatches between the
-  two) only once the model is actually applied, never on the mere click —
+  two) only once the model is actually applied, never on the mere click:
   declining the context-window warning means this exact model cannot work
-  with this CLI at all, so promoting it next time would be actively wrong,
-  not just premature.
+  with this CLI at all, so promoting it next time would be actively
+  wrong, not just premature.
 
-Neither tag reorders anything past that one promoted row. The "Default"
+No promotion reorders anything past that one promoted row. The "Default"
 pill is a separate span, not a third value of the same slot: a promoted
 row that is also the endpoint's `defaultModelId` shows both tags (on a
 single-purpose GPU box that is the common case, and an exclusive slot
 silently dropped the Default marking for exactly that row), and a row
 with neither promotion nor default shows no tag at all.
 
+When nothing is known about any row, `#customModelPickUnknown` says so
+out loud instead of leaving an alphabetical wall that reads as the app
+ignoring the question. It asserts only what the probe actually answered:
+`isLlamaSwap: false` is a real "I cannot tell you", whereas a probe that
+timed out or failed (`_getCustomModelRunningStatus` resolving `null`) is
+not, so an unreachable endpoint stays silent rather than claiming
+something it does not know. Like its sibling no-matches line it needs an
+explicit `[hidden]` rule scoped to `#customModelPickModal`, because
+`.form-hint`'s `display: block` outranks the UA `[hidden]` rule.
+
 **How the launch itself applies the endpoint depends on the harness.** For
 opencode, Codex, Gemini, Pi, Grok, DeepSeek and OMP (`runCustomModelEntry` →
 `_runCustomModelEntryOneShot`), the endpoint/model is folded into the SAME

src/web/public/i18n.js

@@ -627,7 +627,10 @@
     'Custom Endpoints': '自定义端点',
     'Choose a model': '选择模型',
     'Currently loaded': '当前已加载',
+    'In use by a session': '会话正在使用',
     'Last used': '上次使用',
+    'Nothing is marked: this endpoint cannot report which model it has loaded, and no running session uses one. Pick the model to launch, or start a session on this endpoint first.':
+      '未标记任何模型：此端点无法报告它当前加载了哪个模型，并且没有运行中的会话正在使用它。请选择要启动的模型，或先在该端点上启动一个会话。',
     'That endpoint no longer exists': '该端点已不存在',
     'No models discovered for this endpoint yet': '此端点尚未发现任何模型',
     // Model picker search box (index.html placeholder/aria-label and the no-matches line)

src/web/public/index.html

@@ -1041,6 +1041,11 @@
             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>
+          <!-- Shown only when no row carries a loaded/in-use/last-used mark AND the endpoint
+               answered that it is not llama-swap (see _openCustomModelPickModal): it says out
+               loud WHY nothing is marked, in the user's language, rather than leaving an
+               alphabetical wall that looks like the question was ignored. -->
+          <p class="form-hint custom-model-pick-unknown" id="customModelPickUnknown" role="status" hidden>Nothing is marked: this endpoint cannot report which model it has loaded, and no running session uses one. Pick the model to launch, or start a session on this endpoint first.</p>
           <div id="customModelPickList" class="run-mode-custom-models"></div>
         </div>
       </div>

src/web/public/session-ui.js

@@ -1002,12 +1002,20 @@ Object.assign(CodemanApp.prototype, {
   },
 
   /**
-   * Best-effort lookup of the model llama-swap currently has loaded and ready on this
-   * endpoint, so the picker can offer it first instead of making the user remember what
-   * they picked last time it mattered. Mirrors `_watchLlamaSwapLoading`'s own
-   * `state === 'ready'` check. Returns null for a plain (non-llama-swap) server, an
-   * unreachable endpoint, or a loaded model this host no longer lists as discovered —
-   * never throws, since a failed probe should just skip promotion, not break the picker.
+   * Best-effort lookup of what the endpoint itself says it has loaded and ready, so the
+   * picker can offer it first instead of making the user remember what they picked last
+   * time it mattered. Only llama-swap answers this question (the route reads its
+   * `/running`); every other OpenAI-compatible server (a bare llama.cpp, Ollama, vLLM,
+   * or a gateway such as Bifrost fronting a whole fleet) replies `isLlamaSwap: false`,
+   * which is why `_getCustomModelInUseBySession` exists. `state === 'ready'` mirrors
+   * `_watchLlamaSwapLoading`'s own check.
+   *
+   * Resolves the raw route payload rather than a model id so the caller can tell the
+   * three answers apart: llama-swap naming a model, an endpoint that positively cannot
+   * say (safe to explain in the UI), and no answer at all (timeout/unreachable, which
+   * resolves `null` and must NEVER be described as "cannot report", since the endpoint
+   * may well have been asleep rather than mute). Never throws: a failed probe should
+   * just skip promotion, not break the picker.
    *
    * ⚠️ Client-side bounded to ~800ms via Promise.race, on top of (never instead of) the
    * route's own 5s server-side timeout (`RUNNING_TIMEOUT_MS`, custom-model-routes.ts) —
@@ -1024,17 +1032,56 @@ Object.assign(CodemanApp.prototype, {
    * `vi.useFakeTimers()` patches, so a param is the only way to test the timeout without
    * actually waiting on it. Real callers never pass it.
    */
-  async _getCustomModelCurrentlyLoaded(host, timeoutMs = 800) {
+  async _getCustomModelRunningStatus(host, timeoutMs = 800) {
     const probe = this._apiJson(`/api/model-endpoints/${encodeURIComponent(host.id)}/running-status`).catch(
       () => null
     );
     const timeout = new Promise((resolve) => setTimeout(() => resolve(null), timeoutMs));
-    const status = await Promise.race([probe, timeout]);
+    return Promise.race([probe, timeout]);
+  },
+
+  /**
+   * The model llama-swap reports `ready` on this endpoint AND that this host still lists
+   * as discovered (an undropped-but-undiscovered model has no row to promote), else null.
+   */
+  _pickReadyRunningModel(status, host) {
     if (!status?.isLlamaSwap) return null;
     const ready = (status.running || []).find((r) => r.state === 'ready' && (host.models || []).includes(r.model));
     return ready?.model || null;
   },
 
+  /**
+   * The model a LIVE session of this instance is pointed at on `host`, or null. It is the
+   * fallback for every endpoint that cannot answer "what is loaded?" about itself.
+   * A session already running on the endpoint is first-hand evidence of a model in use
+   * there: Codeman itself injected that endpoint and model into it, so it earns the same
+   * promotion llama-swap's own answer gets, under its own honest tag.
+   *
+   * ⚠️ Reads ONLY `customModel` (what Codeman injected), never `displayModel`: that field
+   * is display text scraped off a CLI's footer or statusline for a session header (pane
+   * derived, `source: 'screen'`), and promoting a row because a terminal printed a
+   * similar string is worse than showing nothing.
+   * ⚠️ Requires a live pane: `status: 'stopped'` or a recorded `paneExit` means nothing
+   * is on the endpoint any more, and a dead session's stale pin is exactly what an "in
+   * use" claim must not resurrect. `session:updated` keeps it current, so a session
+   * cleared back to the CLI's own backend or moved to another endpoint stops counting.
+   * ⚠️ A since-deleted endpoint simply matches no host, so no extra liveness check is
+   * needed here.
+   */
+  _getCustomModelInUseBySession(host) {
+    const models = host?.models || [];
+    if (models.length === 0) return null;
+    let newest = null;
+    for (const [, session] of this.sessions || []) {
+      if (!session || session.status === 'stopped' || session.paneExit) continue;
+      const pinned = session.customModel;
+      if (!pinned || pinned.endpointId !== host.id) continue;
+      if (!models.includes(pinned.modelId)) continue; // undiscovered since: no row to promote
+      if (!newest || (newest.createdAt || 0) <= (session.createdAt || 0)) newest = session;
+    }
+    return newest?.customModel?.modelId || null;
+  },
+
   /**
    * Renders the "which model" picker for a (harness, endpoint) pair with more than one
    * discovered model. Async since it now awaits the currently-loaded-model probe below,
@@ -1055,15 +1102,17 @@ Object.assign(CodemanApp.prototype, {
     const generation = (this._customModelPickGeneration = (this._customModelPickGeneration || 0) + 1);
     const isCurrent = () => this._customModelPickGeneration === generation;
 
-    // Whichever model llama-swap actually has loaded right now beats a merely
-    // remembered choice — it's what a launch would attach to with zero wait, while
-    // "last used" might have been swapped out by another session since. Neither
-    // reorders past the top: exactly one model is promoted, everything else keeps
-    // its discovery order.
-    const currentlyLoaded = await this._getCustomModelCurrentlyLoaded(host);
+    // Three kinds of knowledge, best first: what llama-swap says it has loaded right
+    // now (zero wait to attach to), what a live session of this instance is pointed at
+    // on that endpoint (the endpoint itself cannot say, but Codeman put it there), and
+    // only then this device's memory of the last launch. One wins, and it never reorders
+    // anything else: every other row keeps its discovery order.
+    const runningStatus = await this._getCustomModelRunningStatus(host);
     if (!isCurrent()) return; // a newer pick opened (and possibly already rendered) while this probe was in flight
-    const lastUsed = currentlyLoaded ? null : this._getCustomModelLastUsed(mode, host.id);
-    const promoted = currentlyLoaded || lastUsed;
+    const currentlyLoaded = this._pickReadyRunningModel(runningStatus, host);
+    const inUse = currentlyLoaded ? null : this._getCustomModelInUseBySession(host);
+    const lastUsed = currentlyLoaded || inUse ? null : this._getCustomModelLastUsed(mode, host.id);
+    const promoted = currentlyLoaded || inUse || lastUsed;
     const models = [...(host.models || [])];
     if (promoted && models.includes(promoted)) {
       models.splice(models.indexOf(promoted), 1);
@@ -1078,14 +1127,31 @@ Object.assign(CodemanApp.prototype, {
     document.getElementById('customModelPickTitle').textContent = 'Choose a model';
     document.getElementById('customModelPickHint').textContent =
       `${cliLabel} → ${host.label} — ${(host.models || []).length} models discovered.`;
+    // A plain static line (its markup lives in index.html), shown when NOTHING is known
+    // about any row: 40 alphabetical rows with no mark on any of them otherwise read as
+    // the app ignoring the question. It only asserts what the probe actually answered:
+    // `isLlamaSwap: false` is a real "I cannot tell you", where a probe that timed out or
+    // failed (`runningStatus === null`) is not, the box may merely be asleep, so an
+    // unreachable endpoint stays silent instead of explaining something it does not know.
+    const nothingKnown = !promoted && runningStatus?.isLlamaSwap === false;
+    const unknownLine = document.getElementById('customModelPickUnknown');
+    if (unknownLine) unknownLine.hidden = !nothingKnown;
     list.innerHTML = models
       .map((m) => {
-        // Two independent tags, never one exclusive slot: the promotion tag says what
-        // llama-swap (or this device's history) knows about the model, the Default pill
-        // says what the saved endpoint says about it, and on a single-purpose GPU box the
-        // promoted model IS the default more often than not. One slot holding whichever
-        // applied first silently dropped the Default marking for exactly that row.
-        const promotion = m === currentlyLoaded ? 'Currently loaded' : m === lastUsed ? 'Last used' : null;
+        // Two independent tags, never one exclusive slot: the promotion tag says what the
+        // endpoint, a live session, or this device's history knows about the model, the
+        // Default pill says what the saved endpoint says about it, and on a
+        // single-purpose GPU box the promoted model IS the default more often than not.
+        // One slot holding whichever applied first silently dropped the Default marking
+        // for exactly that row.
+        const promotion =
+          m === currentlyLoaded
+            ? 'Currently loaded'
+            : m === inUse
+              ? 'In use by a session'
+              : 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

src/web/public/styles.css

@@ -7824,6 +7824,17 @@ html[data-skin="og"] .welcome-primary:hover {
   padding: 1rem 0;
 }
 
+/* "This endpoint cannot report which model it has loaded": the same `.form-hint`
+   `display: block` beats `[hidden]` trap the two rules below fix for the no-matches
+   line and the filtered rows, so the attribute needs the same re-assertion. */
+#customModelPickModal .custom-model-pick-unknown {
+  padding-bottom: 0.15rem;
+}
+
+#customModelPickModal .custom-model-pick-unknown[hidden] {
+  display: none !important;
+}
+
 /* Same class of bug as the row rule below: the no-matches line carries
    `.form-hint`, whose `display: block` outranks the UA `[hidden]` rule, so
    `filterCustomModelPick()` toggling `hidden` changed nothing on screen and

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

@@ -44,6 +44,8 @@ function bootApp(
     cliAvailable?: (id: string) => boolean;
     activeCase?: { location?: string } | null;
     settingsEnabled?: boolean;
+    /** Live sessions for the "in use by a session" fallback, in `this.sessions` Map shape. */
+    sessions?: Array<Record<string, unknown>>;
   } = {}
 ) {
   const dom = new JSDOM(
@@ -62,6 +64,7 @@ function bootApp(
         <input type="search" id="customModelPickSearch" aria-label="Search models"
           oninput="app.filterCustomModelPick(this.value)">
         <p id="customModelPickNoMatches" role="status" hidden>No models match</p>
+        <p id="customModelPickUnknown" role="status" hidden>Nothing is marked: this endpoint cannot report which model it has loaded, and no running session uses one. Pick the model to launch, or start a session on this endpoint first.</p>
         <div id="customModelPickList"></div>
       </div>
       <div class="modal" id="customModelSwapConfirmModal">
@@ -88,6 +91,10 @@ function bootApp(
   app.cases = options.activeCase ? [{ name: 'testcase', ...options.activeCase }] : [{ name: 'testcase' }];
   app.loadAppSettingsFromStorage = () => ({ customModelEndpointsEnabled: options.settingsEnabled ?? true });
   app.isCliAvailable = options.cliAvailable ?? (() => true);
+  // The real app keeps live sessions in a Map keyed by id (app.js), which is what
+  // _getCustomModelInUseBySession walks; empty by default so a test that says nothing
+  // about sessions sees no promotion, exactly like a box with none running.
+  app.sessions = new Map((options.sessions || []).map((s, i) => [String(i), s]));
   app.showToast = () => {};
   // Real implementation lives in panels-ui.js, not evaluated into this harness (only
   // constants.js + session-ui.js are — see below) — a no-op default handle matching its
@@ -707,7 +714,172 @@ describe('Custom Model Endpoint Profiles: the "which model" picker', () => {
   });
 });
 
-describe('Custom Model Endpoint Profiles: _getCustomModelCurrentlyLoaded is client-side bounded', () => {
+/**
+ * The reported bug: a gateway such as Bifrost (40 models, alphabetical, no llama-swap
+ * `/running` route of its own) showed "Choose a model" with nothing marked, so the user
+ * could not tell which model the endpoint was actually serving, while the same endpoint
+ * reached from the Codex CLI appeared to "default to alpha order" for every other CLI.
+ * The endpoint genuinely cannot answer, so the app falls back to what it does know: a
+ * live session it has itself pointed at that endpoint. And it says so plainly when it
+ * knows neither.
+ */
+describe('Custom Model Endpoint Profiles: gateways without /running fall back to a live session', () => {
+  const GATEWAY = {
+    id: 'bifrost',
+    label: 'bifrost',
+    baseUrl: 'https://bifrost.example',
+    models: ['llama-swap/alpha-3b', 'llama-swap/qwen3.8-flash-next-unsloth-ud-iq4_xs', 'llama-swap/zeta-70b'],
+  };
+
+  /** The gateway's exact shape: reachable, OpenAI-compatible, and not llama-swap. */
+  function gatewayApp(sessions: Array<Record<string, unknown>>) {
+    const booted = bootApp({ hosts: [GATEWAY], sessions });
+    const origApiJson = booted.app._apiJson;
+    booted.app._apiJson = async (path: string) => {
+      if (path === '/api/model-endpoints/bifrost/running-status') return { isLlamaSwap: false, running: [] };
+      return origApiJson(path);
+    };
+    return booted;
+  }
+
+  const live = (modelId: string, overrides: Record<string, unknown> = {}) => ({
+    name: 'w9-Gateway',
+    status: 'busy',
+    createdAt: 1_700_000_000_000,
+    customModel: { endpointId: 'bifrost', modelId, label: 'bifrost' },
+    ...overrides,
+  });
+
+  it('marks the model a live session is running, at the top, for EVERY CLI, not just claude', async () => {
+    const inUse = 'llama-swap/qwen3.8-flash-next-unsloth-ud-iq4_xs';
+    for (const mode of ['opencode', 'deepseek', 'codex', 'claude']) {
+      const { win, app } = gatewayApp([live(inUse)]);
+      await app._openCustomModelPickModal(mode, GATEWAY);
+      const buttons = [...win.document.getElementById('customModelPickList')!.querySelectorAll('button')];
+      expect(buttons).toHaveLength(3);
+      expect(buttons[0].textContent, mode).toContain(inUse);
+      expect(buttons[0].textContent, mode).toContain('In use by a session');
+      // The other rows keep discovery order and carry no tag of their own.
+      expect(buttons[1].textContent).toContain('llama-swap/alpha-3b');
+      expect(buttons[2].querySelectorAll('.set-scope')).toHaveLength(0);
+      // Nothing was fabricated about the endpoint itself.
+      expect(win.document.getElementById('customModelPickList')!.textContent).not.toContain('Currently loaded');
+      expect(win.document.getElementById('customModelPickUnknown')!.hasAttribute('hidden')).toBe(true);
+    }
+  });
+
+  it('a live session outranks this device’s "last used" memory, and both rank above nothing', async () => {
+    const { win, app } = gatewayApp([live('llama-swap/zeta-70b')]);
+    win.localStorage.setItem('codeman:customModelLastUsed:opencode:bifrost', 'llama-swap/alpha-3b');
+
+    await app._openCustomModelPickModal('opencode', GATEWAY);
+
+    const buttons = [...win.document.getElementById('customModelPickList')!.querySelectorAll('button')];
+    expect(buttons[0].textContent).toContain('llama-swap/zeta-70b');
+    expect(buttons[0].textContent).toContain('In use by a session');
+    expect(buttons[0].textContent).not.toContain('Last used');
+    // The remembered pick is still listed, just not promoted or double-tagged.
+    expect(buttons[1].textContent).toContain('llama-swap/alpha-3b');
+    expect(buttons[1].querySelectorAll('.set-scope')).toHaveLength(0);
+  });
+
+  it('a stopped session, an exited pane, another endpoint or an undiscovered model mark nothing', async () => {
+    const inUse = 'llama-swap/qwen3.8-flash-next-unsloth-ud-iq4_xs';
+    const cases: Array<[string, Record<string, unknown>]> = [
+      ['stopped', { status: 'stopped' }],
+      ['pane exited', { paneExit: { at: 1, status: 0 } }],
+      ['other endpoint', { customModel: { endpointId: 'other', modelId: inUse } }],
+      ['no custom model', { customModel: undefined }],
+      ['undiscovered model', { customModel: { endpointId: 'bifrost', modelId: 'llama-swap/retired-model' } }],
+    ];
+    for (const [label, overrides] of cases) {
+      const { win, app } = gatewayApp([live(inUse, overrides)]);
+      await app._openCustomModelPickModal('opencode', GATEWAY);
+      const list = win.document.getElementById('customModelPickList')!;
+      expect(list.textContent, label).not.toContain('In use by a session');
+      expect(list.textContent, label).not.toContain('Last used');
+      // Discovery order untouched: nothing got dragged to the top.
+      expect(list.querySelectorAll('button')![0].textContent).toContain('llama-swap/alpha-3b');
+    }
+  });
+
+  it('the most recently launched live session wins when two share an endpoint', async () => {
+    const { win, app } = gatewayApp([
+      live('llama-swap/alpha-3b', { createdAt: 1 }),
+      live('llama-swap/zeta-70b', { createdAt: 2 }),
+    ]);
+
+    await app._openCustomModelPickModal('opencode', GATEWAY);
+
+    const buttons = [...win.document.getElementById('customModelPickList')!.querySelectorAll('button')];
+    expect(buttons[0].textContent).toContain('llama-swap/zeta-70b');
+    expect(buttons.filter((b) => b.textContent!.includes('In use by a session'))).toHaveLength(1);
+  });
+
+  it('says so plainly when the endpoint cannot report a loaded model and nothing is known', async () => {
+    const { win, app } = gatewayApp([]);
+
+    await app._openCustomModelPickModal('opencode', GATEWAY);
+
+    const unknown = win.document.getElementById('customModelPickUnknown')!;
+    expect(unknown.hasAttribute('hidden')).toBe(false);
+    expect(unknown.textContent).toContain('cannot report which model it has loaded');
+    // The same class-of-bug trap as the no-matches line: `.form-hint`'s `display: block`
+    // outranks the UA `[hidden]` rule, so the attribute needs the CSS re-assertion.
+    const rule = STYLES_CSS.match(/#customModelPickModal \.custom-model-pick-unknown\[hidden\]\s*\{[^}]*\}/);
+    expect(rule, 'the unknown-endpoint line needs a [hidden] rule scoped to #customModelPickModal').toBeTruthy();
+    expect(rule![0]).toMatch(/display:\s*none\s*!important/);
+  });
+
+  it('hides that line whenever a row IS marked, and stays silent for an endpoint that never answered', async () => {
+    // Marked by a live session: nothing to explain.
+    const marked = gatewayApp([live('llama-swap/alpha-3b')]);
+    await marked.app._openCustomModelPickModal('opencode', GATEWAY);
+    expect(marked.win.document.getElementById('customModelPickUnknown')!.hasAttribute('hidden')).toBe(true);
+
+    // Probe timed out (`null`) rather than answered "not llama-swap": the endpoint may
+    // merely be asleep, so claiming it cannot report would be a guess.
+    const asleep = bootApp({ hosts: [GATEWAY] });
+    asleep.app._apiJson = async (path: string) => (path.includes('running-status') ? null : []);
+    await asleep.app._openCustomModelPickModal('opencode', GATEWAY);
+    expect(asleep.win.document.getElementById('customModelPickUnknown')!.hasAttribute('hidden')).toBe(true);
+  });
+
+  it('llama-swap’s own answer still wins over a session pin, and keeps its own tag', async () => {
+    const booted = bootApp({
+      hosts: [GATEWAY],
+      sessions: [live('llama-swap/alpha-3b')],
+    });
+    const origApiJson = booted.app._apiJson;
+    booted.app._apiJson = async (path: string) => {
+      if (path === '/api/model-endpoints/bifrost/running-status') {
+        return { isLlamaSwap: true, running: [{ model: 'llama-swap/zeta-70b', state: 'ready' }] };
+      }
+      return origApiJson(path);
+    };
+
+    await booted.app._openCustomModelPickModal('opencode', GATEWAY);
+
+    const buttons = [...booted.win.document.getElementById('customModelPickList')!.querySelectorAll('button')];
+    expect(buttons[0].textContent).toContain('llama-swap/zeta-70b');
+    expect(buttons[0].textContent).toContain('Currently loaded');
+    expect(buttons[0].textContent).not.toContain('In use by a session');
+    // The session's model is an ordinary row again: one promotion, not two.
+    expect(buttons.filter((b) => b.querySelector('.set-scope'))).toHaveLength(1);
+  });
+
+  it('never trusts displayModel: a session whose terminal merely printed a model marks nothing', async () => {
+    const booted = gatewayApp([
+      { name: 'w9-Other', status: 'busy', createdAt: 1, displayModel: { model: 'llama-swap/zeta-70b', source: 'screen' } },
+    ]);
+
+    await booted.app._openCustomModelPickModal('opencode', GATEWAY);
+
+    expect(booted.win.document.getElementById('customModelPickList')!.textContent).not.toContain('In use by a session');
+  });
+});
+
+describe('Custom Model Endpoint Profiles: _getCustomModelRunningStatus is client-side bounded', () => {
   // `timeoutMs` driven in milliseconds rather than the real 800 — same reasoning as
   // `_watchLlamaSwapLoading`'s own `pollIntervalMs` a few describe blocks down: this
   // code runs inside the JSDOM window's own realm, whose setTimeout vi.useFakeTimers()
@@ -722,26 +894,30 @@ describe('Custom Model Endpoint Profiles: _getCustomModelCurrentlyLoaded is clie
     // endpoint that is asleep or firewalled, distinct from one that answers an error.
     app._apiJson = () => new Promise(() => {});
 
-    const result = await app._getCustomModelCurrentlyLoaded({ id: 'llama-box', models: ['qwen3'] }, 5);
+    const status = await app._getCustomModelRunningStatus({ id: 'llama-box', models: ['qwen3'] }, 5);
 
-    expect(result).toBeNull();
+    // `null` means "no answer", which is NOT the same as an endpoint that answered that
+    // it cannot report: the picker keeps its "this endpoint cannot report" line hidden
+    // for exactly this case (pinned below).
+    expect(status).toBeNull();
+    expect(app._pickReadyRunningModel(status, { id: 'llama-box', models: ['qwen3'] })).toBeNull();
   });
 
   it('an endpoint that answers well within the bound is unaffected by it', async () => {
     const { app } = bootApp({});
     app._apiJson = async () => ({ isLlamaSwap: true, running: [{ model: 'qwen3', state: 'ready' }] });
 
-    const result = await app._getCustomModelCurrentlyLoaded({ id: 'llama-box', models: ['qwen3'] }, 5);
+    const status = await app._getCustomModelRunningStatus({ id: 'llama-box', models: ['qwen3'] }, 5);
 
-    expect(result).toBe('qwen3');
+    expect(app._pickReadyRunningModel(status, { id: 'llama-box', models: ['qwen3'] })).toBe('qwen3');
   });
 
   it('a rejected probe settles quietly to null rather than leaving an unhandled rejection once the timeout has already won the race', async () => {
     const { app } = bootApp({});
     app._apiJson = () => new Promise((_resolve, reject) => setTimeout(() => reject(new Error('boom')), 10));
 
-    const result = await app._getCustomModelCurrentlyLoaded({ id: 'llama-box', models: ['qwen3'] }, 2);
-    expect(result).toBeNull();
+    const status = await app._getCustomModelRunningStatus({ id: 'llama-box', models: ['qwen3'] }, 2);
+    expect(status).toBeNull();
     // Give the loser of the race a turn to actually reject and hit its own .catch —
     // an unswallowed rejection here would surface as an "Unhandled Errors" failure
     // for the whole test file, not a failed assertion in this test.