aegis-desktop 0.7.6 → 0.7.8

package/lib/local/engine.js

@@ -45,6 +45,10 @@ const os = require('node:os');
 
 const toolsModule = require('./tools.js');
 const promptModule = require('./prompt.js');
+// The direct-dial policy: which base URLs may reach a provider transport, and
+// why a remote one is refused rather than metered. The same module the CLI
+// resolves (cli/src/custommodels.js), so both hosts answer with one rule.
+const { isLocalEndpoint, remoteRefusal } = require('./endpoints.js');
 const { ShellSession } = require('./shell.js');
 const { agentSystemPrompt, agentRoleLabel } = require('./agents.js');
 // Cooperative working-tree sharing (see each module's header). The lock
@@ -87,8 +91,28 @@ const CLASSES = [
   { class: 'ollama', label: 'Ollama (local)', kind: 'local' },
   { class: 'openai-compat', label: 'Custom OpenAI-compatible', kind: 'custom' },
   { class: 'anthropic', label: 'Anthropic-compatible', kind: 'custom' },
+  { class: 'byok', label: 'Bring your own key', kind: 'cloud' },
 ];
 
+/** Local settings namespace for one BYOK provider's key. A `byok:` prefix
+ *  keeps this out of the 'anthropic'/'openai-compat' CUSTOM_CLASSES' own
+ *  namespaces, which are a different feature (a self-hosted/compatible
+ *  endpoint's base URL + key) — same store, deliberately separate rows. */
+function byokNamespace(providerId) {
+  return `byok:${providerId}`;
+}
+
+/** Split a byok model id ("anthropic:claude-sonnet-5") into its provider and
+ *  bare model parts. `modelId` may itself contain ':' (none of today's
+ *  catalog ids do, but nothing guarantees that), so only the FIRST segment is
+ *  the provider — the rest re-joins as the model. */
+function splitByokModel(compound) {
+  const s = typeof compound === 'string' ? compound : '';
+  const i = s.indexOf(':');
+  if (i < 0) return { provider: '', model: s };
+  return { provider: s.slice(0, i), model: s.slice(i + 1) };
+}
+
 /**
  * Mirrors aegiscodex-dev's src/backend.js DEEPSEEK_REASONING_MODEL_RE +
  * EFFORT_TOKEN_BUDGET verbatim. DeepSeek's reasoning models (deepseek-flash,
@@ -637,14 +661,26 @@ function createLocalEngine({ aegis, settings, ollama, providers, tools, promptBu
    * a base URL is mandatory for both, and Anthropic additionally needs its own
    * key (the wire format authenticates with x-api-key). Reporting them as
    * always-ready made chat() POST to `${undefined}/v1/…` (defect #2).
+   *
+   * A stored REMOTE base URL is reported as not-configured rather than ready,
+   * plus `blocked` and the reason. This is the third face of the direct-dial
+   * gate (storage in settings.js set, dispatch in chat below): a row that
+   * predates the rule must not be OFFERED either, or the class list advertises
+   * a lane the turn then refuses. The reason travels so the UI can explain it
+   * instead of showing a dead row — and it is recoverable by design: saving a
+   * local URL (or clearing the field) makes the class usable again, which is
+   * what the refusal text tells the user to do.
    */
   function customStatus(cls) {
     const cfg = settings.get(cls) || {};
     const baseURL = typeof cfg.baseURL === 'string' ? cfg.baseURL.trim() : '';
     const hasBase = Boolean(baseURL);
     const hasKey = Boolean(cfg.configured);
+    const blocked = hasBase && !isLocalEndpoint(baseURL);
     return {
-      configured: cls === 'anthropic' ? hasBase && hasKey : hasBase,
+      configured: !blocked && (cls === 'anthropic' ? hasBase && hasKey : hasBase),
+      blocked,
+      ...(blocked ? { blockedReason: remoteRefusal(baseURL, { subject: `the ${cls} endpoint` }) } : {}),
       baseURL,
       keyMask: cfg.keyMask || null,
     };
@@ -657,6 +693,16 @@ function createLocalEngine({ aegis, settings, ollama, providers, tools, promptBu
       if (c.class === 'aegis') {
         return { ...c, configured: Boolean(aegis.apiKey) };
       }
+      if (c.class === 'byok') {
+        // Configured means "at least one provider has a locally-stored key",
+        // not a single baseURL+key pair like the CUSTOM_CLASSES below — byok
+        // holds one row per provider (byokNamespace), so customStatus's shape
+        // does not apply here.
+        const anyConfigured = (settings.list() || []).some(
+          (s) => s && typeof s.provider === 'string' && s.provider.startsWith('byok:') && s.configured
+        );
+        return { ...c, configured: anyConfigured };
+      }
       return { ...c, ...customStatus(c.class) };
     });
   }
@@ -681,6 +727,56 @@ function createLocalEngine({ aegis, settings, ollama, providers, tools, promptBu
       const tags = await ollama.listTags();
       return { class: cls, models: tags.map((t) => ({ id: t.id })) };
     }
+    if (cls === 'byok') {
+      // The server's catalog names every provider it accepts a key for, the
+      // models each unlocks, and whether an AEGIS account key is even needed
+      // to ask (it is not — the catalog answers an anonymous request).
+      // Deliberately NOT gated on aegis.apiKey the way the pooled class above
+      // is: BYOK's whole point is a caller who brings their own credential, and
+      // hiding the catalog would hide the answer to "which key do I go and get"
+      // from exactly the person deciding whether to bother. Nothing here
+      // enforces billing either: the desktop is one client of a route that is
+      // unauthenticated by design, so refusing in this process would stop
+      // exactly one host out of many. The relay owns that decision, and reports
+      // it via `fee.require_balance` below.
+      let providers = [];
+      let fee = null;
+      try {
+        const data = await aegis.byokProviders();
+        providers = (data && data.providers) || [];
+        // The handling fee AEGIS adds on top of the caller's vendor bill. It is
+        // the server's own published rate (services/pricing.price_byok_call) and
+        // is passed through untouched — never re-derived here, because a client
+        // that hardcodes a fee is a client that can disagree with the ledger.
+        // Absent until the server publishes one, and the UI must then say
+        // nothing rather than show a guess.
+        fee = (data && data.fee) || null;
+      } catch {
+        providers = [];
+      }
+      const models = [];
+      for (const p of providers) {
+        if (!p || !p.id) continue;
+        const local = settings.get(byokNamespace(p.id)) || {};
+        const rawModels = Array.isArray(p.models) ? p.models : [];
+        for (const m of rawModels) {
+          const modelId = typeof m === 'string' ? m : m && m.id;
+          if (!modelId) continue;
+          models.push({
+            id: `${p.id}:${modelId}`,
+            label: `${p.label || p.id} — ${modelId}`,
+            provider: p.id,
+            configured: Boolean(local.configured),
+          });
+        }
+      }
+      return {
+        class: cls, models, providers,
+        needsProviderKey: models.length > 0 && !models.some((m) => m.configured),
+        needsAegisKey: !aegis.apiKey,
+        fee,
+      };
+    }
     // Custom endpoints: the model id is the *user's* choice — a provider model
     // name, never a URL. Offering the configured base URL as an `id` meant that
     // leaving the default selection POSTed `model: "https://api.openai.com/v1"`,
@@ -690,7 +786,18 @@ function createLocalEngine({ aegis, settings, ollama, providers, tools, promptBu
     // along for display only.
     const cfg = settings.get(cls) || {};
     const baseURL = typeof cfg.baseURL === 'string' ? cfg.baseURL.trim() : '';
-    return { class: cls, models: [], needsModelId: true, baseURL };
+    // Same reporting as customStatus: a stored remote URL is not a usable
+    // model list, and the reason has to reach the UI with it (see customStatus).
+    const blocked = Boolean(baseURL) && !isLocalEndpoint(baseURL);
+    return {
+      class: cls,
+      models: [],
+      needsModelId: true,
+      baseURL,
+      ...(blocked
+        ? { blocked: true, blockedReason: remoteRefusal(baseURL, { subject: `the ${cls} endpoint` }) }
+        : {}),
+    };
   }
 
   /**
@@ -867,6 +974,53 @@ function createLocalEngine({ aegis, settings, ollama, providers, tools, promptBu
       });
     }
 
+    if (cls === 'byok') {
+      // opts.model is still the compound "provider:model" id here — the
+      // relay wants them split (a `provider` field plus a bare `model`).
+      // opts.apiKey is the PROVIDER key resolved by chat() above (from the
+      // byokNamespace(provider) settings row), never the account's own AEGIS
+      // key — that one is baked into the `aegis` client already and attached
+      // automatically by byokChatCompletion() as X-AEGIS-Key so the account
+      // gets billed the handling fee; see client/aegis.js.
+      const { provider, model: bareModel } = splitByokModel(opts.model);
+      try {
+        return await aegis.byokChatCompletion({
+          provider,
+          model: bareModel,
+          providerKey: opts.apiKey,
+          prompt: opts.prompt,
+          system: opts.system,
+          messages: opts.messages,
+          maxTokens: opts.maxTokens,
+          stream: true,
+          onStream: opts.onDelta,
+          signal: opts.signal,
+        });
+      } catch (e) {
+        // The relay's own balance gate (aegis1 `AEGIS_BYOK_REQUIRE_BALANCE`,
+        // app.py `byok_chat_completions`) answers 402 with a body aimed at an
+        // API consumer — "Insufficient balance. Top up to continue using
+        // BYOK." Shown raw in a chat transcript that reads as a crash rather
+        // than a bill, so the one thing the user has to DO is said here, in the
+        // hosts' own voice. The status is preserved so every existing caller
+        // (the CLI's error painter, the desktop turn guard) still sees a 402.
+        //
+        // The provider key is untouched by this: it is the caller's own and it
+        // is still valid. What ran out is the AEGIS balance the handling fee
+        // is billed against, which is the whole reason this lane has a fee.
+        if (e && e.status === 402) {
+          const err = new Error(
+            'byok: this account has no AEGIS balance left, and the BYOK handling fee is ' +
+              'billed there — your provider key is still valid, this is not a key problem. ' +
+              'Top up the account, then try again (or /class aegis to use the pooled lane).'
+          );
+          err.status = 402;
+          throw err;
+        }
+        throw e;
+      }
+    }
+
     const common = {
       baseURL: opts.cfg.baseURL,
       apiKey: opts.apiKey,
@@ -887,7 +1041,14 @@ function createLocalEngine({ aegis, settings, ollama, providers, tools, promptBu
   async function chat(payload, onDelta) {
     const cls = payload && payload.class;
     const model = payload && payload.model;
-    const maxTokens = reasoningBudget(cls, model, payload && payload.maxTokens, payload && payload.effort);
+    // byok's model id is "provider:model" (see splitByokModel) — strip the
+    // provider prefix before pattern-matching, or a DeepSeek reasoning model
+    // selected under byok ("byok" model "deepseek:deepseek-v4-flash") never
+    // matches DEEPSEEK_REASONING_MODEL_RE's anchored pattern and silently
+    // gets no stated budget, which is exactly the "hidden CoT ate the whole
+    // default and returned nothing" failure this budget exists to prevent.
+    const reasoningModelId = cls === 'byok' ? splitByokModel(model).model : model;
+    const maxTokens = reasoningBudget(cls, reasoningModelId, payload && payload.maxTokens, payload && payload.effort);
     // The caller's OWN number, kept apart from `maxTokens` above. That one
     // collapses two different facts into a single value — "the caller stated
     // 4096" and "effort implies 32768" — and the pooled path must treat them
@@ -937,8 +1098,12 @@ function createLocalEngine({ aegis, settings, ollama, providers, tools, promptBu
     const signal = controller.signal;
 
     // A caller can opt out of the agent loop entirely (`tools: false`) and get
-    // the old single-shot turn back.
-    const toolsEnabled = !(payload && payload.tools === false);
+    // the old single-shot turn back. byok is ALWAYS single-shot: the
+    // stateless relay (aegis.byokChatCompletion, /api/v1/byok/chat/completions)
+    // has no tools/tool_choice parameter at all, so sending schemas here would
+    // build a prompt promising tool access the transport silently drops —
+    // the model would reason about exec/readFile and never see a result.
+    const toolsEnabled = cls !== 'byok' && !(payload && payload.tools === false);
     const wire = cls === 'anthropic' ? 'anthropic' : 'openai';
     const toolSchemas = toolsEnabled ? T.toolsFor(wire, { includeSubagent: depth < MAX_SUBAGENT_DEPTH }) : [];
     const toolChoice = (payload && payload.toolChoice) || null;
@@ -965,8 +1130,89 @@ function createLocalEngine({ aegis, settings, ollama, providers, tools, promptBu
     const turnCwd = envFor(payload).cwd;
 
     try {
-      const cfg = cls === 'aegis' || cls === 'ollama' ? {} : settings.get(cls) || {};
-      const apiKey = cls === 'aegis' || cls === 'ollama' ? null : settings.rawKey(cls);
+      // byok's settings row lives under the provider named IN THE MODEL id
+      // ("anthropic:claude-sonnet-5" -> byokNamespace('anthropic')), never
+      // under the literal class name — one flat 'byok' row could not hold
+      // more than one provider's key at a time.
+      const byokParts = cls === 'byok' ? splitByokModel(model) : null;
+      const cfg =
+        cls === 'aegis' || cls === 'ollama' ? {}
+        : cls === 'byok' ? settings.get(byokNamespace(byokParts.provider)) || {}
+        : settings.get(cls) || {};
+      const apiKey =
+        cls === 'aegis' || cls === 'ollama' ? null
+        : cls === 'byok' ? settings.rawKey(byokNamespace(byokParts.provider))
+        : settings.rawKey(cls);
+
+      if (cls === 'byok' && (!byokParts.provider || !byokParts.model)) {
+        const err = new Error(
+          "byok: model must be \"<provider>:<model>\" (pick one from /models) — got " +
+            JSON.stringify(model || '')
+        );
+        err.status = 400;
+        throw err;
+      }
+      if (cls === 'byok' && !apiKey) {
+        const err = new Error(
+          `byok: no key saved for "${byokParts.provider}" — add one before chatting with this model.`
+        );
+        err.status = 400;
+        throw err;
+      }
+      // …and the AEGIS account key is what makes the turn BILLABLE at all. The
+      // relay authenticates on the provider key and resolves the payer
+      // separately, from X-AEGIS-Key (app.py `_byok_identify_user`): with no
+      // account key the server can attribute the handling fee to no one, so it
+      // is logged against user 0 as uncollected — an anonymous free ride the
+      // fee exists to close. Require the account key here so EVERY BYOK turn is
+      // attributed and every caller pays the handling fee: a funded balance is
+      // debited immediately, an unfunded one records the fee as owed
+      // (token_bank.charge_byok clamps to zero and never refuses), and nobody
+      // is served free. Balance is the server's own concern, not this gate's —
+      // with a balance or without one, the account still pays. `listModels`
+      // still answers anonymously (the catalog is how a user finds out which
+      // key to get), so this refuses only the send, and only until a key lands.
+      if (cls === 'byok' && !aegis.apiKey) {
+        const err = new Error(
+          'byok: connect your AEGIS account key first — the BYOK handling fee is billed there. ' +
+            'Add it in the Status card (or run /login), then try again.'
+        );
+        err.status = 401;
+        throw err;
+      }
+
+      // THE DIRECT-DIAL GATE. A custom class talks to the user's base URL
+      // itself (providers.js openaiCompatible / anthropicMessages), and that
+      // transport bills NOBODY: no pooled margin, no BYOK handling fee, no
+      // account key attached. The only usage it may therefore carry is an
+      // endpoint on this machine, where there is no vendor to pay. A remote URL
+      // here is an unpaid turn, and it is refused rather than metered because
+      // there is nothing to meter it against — the relay accepts a fixed
+      // catalog of provider ids (services/nexus_provider/catalog.py), so an
+      // arbitrary remote URL cannot be billed there either.
+      //
+      // Checked at DISPATCH and not only at storage (settings.js set refuses
+      // the same URL): a row written before this rule existed, or hand-edited
+      // into settings.json, is still in the file, and reading it back happily
+      // would keep the lane open. Both seams, one rule — the message is
+      // endpoints.js's, so the desktop and the CLI say the same thing.
+      if (CUSTOM_CLASSES.includes(cls)) {
+        const raw = cfg && typeof cfg.baseURL === 'string' ? cfg.baseURL.trim() : '';
+        if (raw && !isLocalEndpoint(raw)) {
+          const err = new Error(
+            remoteRefusal(raw, {
+              subject: `the ${cls} endpoint`,
+              hint:
+                'This class dials your URL directly and bills nobody, so it is local-only. ' +
+                'Use a model on this machine, or move the provider to the BYOK card (/class byok), ' +
+                'which relays through AEGIS and charges the handling fee.',
+            })
+          );
+          err.status = 400;
+          err.code = 'CUSTOM_ENDPOINT_NOT_LOCAL';
+          throw err;
+        }
+      }
 
       // Custom classes carry no enumerable model list (see listModels), so a
       // blank id here means the user never typed one. Fail loudly in-process

package/lib/settings.js

@@ -17,6 +17,12 @@
 
 const fs = require('node:fs');
 const path = require('node:path');
+// The direct-dial policy (see that file): which rows may hold a remote base URL.
+// Enforced HERE, at the storage seam, so the unusable configuration cannot be
+// created by either host — the desktop's Settings pane or the CLI's `/model add`
+// — rather than only being refused at send time. Pure node builtins, so this
+// store stays loadable without Electron.
+const { isLocalEndpoint, remoteRefusal, isDirectDialRow } = require('./local/endpoints.js');
 
 const SETTINGS_FILE = 'settings.json';
 
@@ -124,8 +130,13 @@ function createSettingsStore({ dir, safeStorage } = {}) {
   function save(data) {
     fs.mkdirSync(path.dirname(file), { recursive: true });
     const tmp = `${file}.tmp-${process.pid}`;
-    fs.writeFileSync(tmp, JSON.stringify(data, null, 2));
+    // 0600, written before the rename so the file is never briefly readable:
+    // this store holds provider keys, and both hosts are now able to write it
+    // (the CLI uses the same file, without Electron's safeStorage, so at-rest
+    // base64 is all the protection there is — file mode is the real control).
+    fs.writeFileSync(tmp, JSON.stringify(data, null, 2), { mode: 0o600 });
     fs.renameSync(tmp, file);
+    try { fs.chmodSync(file, 0o600); } catch {}
   }
 
   /** Provider CRUD must never touch a reserved (AEGIS-key) namespace. */
@@ -149,8 +160,38 @@ function createSettingsStore({ dir, safeStorage } = {}) {
     };
   }
 
+  /**
+   * Write a provider row.
+   *
+   * A direct-dial row ('openai-compat', 'anthropic', 'custom:*') may not hold a
+   * remote base URL: those classes talk to the URL themselves (providers.js),
+   * which bills nobody, so the only usage they may carry is an endpoint on this
+   * machine. Refusing at STORAGE — the earliest seam, shared by the desktop's
+   * Settings pane and the CLI — means a remote custom endpoint cannot be
+   * configured into existence in the first place; the engine's dispatch gate
+   * then covers the rows that predate this rule or were hand-edited into the
+   * file. Empty is allowed (that is how the row is cleared, and how a
+   * not-yet-configured row looks), and every other namespace is untouched:
+   * `byok:<provider>` rows are remote by definition and reach their provider
+   * through AEGIS's relay, which is what bills them.
+   */
   function set(provider, { baseURL, key } = {}) {
     assertNotReserved(provider);
+    if (baseURL !== undefined && isDirectDialRow(provider)) {
+      const next = String(baseURL == null ? '' : baseURL).trim();
+      if (next && !isLocalEndpoint(next)) {
+        const err = new Error(remoteRefusal(next, {
+          subject: `the ${provider} endpoint`,
+          hint:
+            'This lane is for a model running on this machine. To use a remote provider, ' +
+            'save it under Bring-your-own-key (the CLI\'s /class byok), where the AEGIS handling ' +
+            'fee bills the turn.',
+        }));
+        err.status = 400;
+        err.code = 'CUSTOM_ENDPOINT_NOT_LOCAL';
+        throw err;
+      }
+    }
     const data = load();
     const cfg = data[provider] || {};
     if (baseURL !== undefined) cfg.baseURL = baseURL;

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "aegis-desktop",
   "productName": "AEGIS Desktop",
-  "version": "0.7.6",
+  "version": "0.7.8",
   "description": "Thin Electron host for AEGIS — a local chat UI over the shared client/aegis.js transport. Ships transport + UI only; engine logic stays server-side.",
   "author": {
     "name": "AEGIS Code",
@@ -29,7 +29,7 @@
     "icon": "node scripts/generate-icon.mjs",
     "dist": "npm run predist && electron-builder",
     "dist:dir": "npm run predist && electron-builder --dir",
-    "check": "node --check main.js && node --check preload.js && node --check renderer/app.js && node --check renderer/quick.js && node --check renderer/budget.js && node --check renderer/usage.js && node --check renderer/stream-policy.js && node --check renderer/transcript-view.js && node --check renderer/diff.js && node --check renderer/diffview.js && node --check renderer/markdown.js && node --check renderer/vendor/aegis-highlight.js && node --check scripts/predist.mjs && node --check scripts/generate-icon.mjs && node --check lib/local/context.js && node --check lib/local/providers.js && node --check lib/local/ollama.js && node --check lib/local/engine.js && node --check lib/local/session-rounds.js && node --check lib/local/tools.js && node --check lib/local/prompt.js && node --check lib/local/shell.js && node --check lib/local/agents.js && node --check lib/local/queue.js && node --check lib/local/autonomous.js && node --check lib/settings.js && node --check lib/sync/sessions.js && node --check lib/sync/memory-queue.js && node --check lib/window-state.js && node --check lib/deep-link.js && node --check lib/quick-launcher.js && node --check bin/aegis.js",
+    "check": "node --check main.js && node --check preload.js && node --check renderer/app.js && node --check renderer/quick.js && node --check renderer/budget.js && node --check renderer/usage.js && node --check renderer/stream-policy.js && node --check renderer/transcript-view.js && node --check renderer/preset-fill.js && node --check renderer/diff.js && node --check renderer/diffview.js && node --check renderer/markdown.js && node --check renderer/vendor/aegis-highlight.js && node --check scripts/predist.mjs && node --check scripts/generate-icon.mjs && node --check lib/local/context.js && node --check lib/local/providers.js && node --check lib/local/ollama.js && node --check lib/local/engine.js && node --check lib/local/endpoints.js && node --check lib/local/session-rounds.js && node --check lib/local/tools.js && node --check lib/local/prompt.js && node --check lib/local/shell.js && node --check lib/local/agents.js && node --check lib/local/queue.js && node --check lib/local/autonomous.js && node --check lib/settings.js && node --check lib/sync/sessions.js && node --check lib/sync/memory-queue.js && node --check lib/window-state.js && node --check lib/deep-link.js && node --check lib/quick-launcher.js && node --check bin/aegis.js",
     "test:shell": "node ../test/desktop-shell.mjs",
     "test:model": "node ../test/model-dispatch.mjs",
     "test:budget": "node ../test/budget.test.mjs",
@@ -43,7 +43,8 @@
     "test:preview-read": "node ../test/desktop-preview-read.test.mjs",
     "test:stream-policy": "node ../test/stream-policy.test.mjs",
     "test:renderer-dom": "node ../test/renderer-dom.test.mjs",
-    "test:renderer-wiring": "node ../test/renderer-wiring.test.mjs"
+    "test:renderer-wiring": "node ../test/renderer-wiring.test.mjs",
+    "test:preset-fill": "node ../test/preset-fill.test.mjs"
   },
   "dependencies": {
     "electron": "^33.0.0",