Merge pull request #757: feat(custom-model): mark the model a session is using in the endpoint model picker

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 did not report which model it has loaded, and none of your running sessions uses one. Pick the model to launch.':
+      '未标记任何模型：此端点没有报告它已加载了哪个模型，你运行中的会话也没有在使用它。请选择要启动的模型。',
     '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 did not report which model it has loaded, and none of your running sessions uses one. Pick the model to launch.</p>
           <div id="customModelPickList" class="run-mode-custom-models"></div>
         </div>
       </div>

src/web/public/session-ui.js

@@ -1002,12 +1002,23 @@ 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; `isLlamaSwap: false`, which is what
+   * the route answers for EVERY failure it catches (a server without a `/running`
+   * route, a refused or unresolvable endpoint, a 401 from a wrong key) — safe to
+   * explain in the UI as long as the wording also fits an endpoint that is down; and
+   * `null`, only when Codeman's own request to the route failed or the client-side
+   * bound below won the race, which stays silent, since the endpoint may merely have
+   * been asleep. 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 +1035,58 @@ 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'`, a null `pid` (the PTY exited; the
+   * same live-pane test keep-warm applies, `src/prompt-cache-keepwarm.ts`) 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.pid === null || 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 +1107,17 @@ 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 +1132,37 @@ 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. `isLlamaSwap: false` is what the route answers for
+    // every failure it catches: a server that cannot report AND a down or refused one
+    // alike (`getLlamaSwapStatus`, custom-model-routes.ts), so the line's wording
+    // promises only that nothing was reported, which stays true either way. A probe
+    // that never got an answer at all (`runningStatus === null`: Codeman's own request
+    // failed or the 800ms bound won) keeps the line hidden, the box may merely be
+    // asleep.
+    // A remembered id that has since vanished from host.models is no promotion: count
+    // only a promoted id that is actually a row, or a stale "last used" would both skip
+    // tagging any row and hide this line, leaving 40 unmarked rows with no explanation.
+    const nothingKnown = !(promoted && models.includes(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

@@ -7831,6 +7831,17 @@ html[data-skin="og"] .welcome-primary:hover {
   padding: 1rem 0;
 }
 
+/* "Nothing is marked: this endpoint did not 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