open-agents-ai 0.103.37 → 0.103.38

package/dist/index.js

@@ -12607,30 +12607,74 @@ async function handleCmd(cmd) {
           dlog('expose: auth key configured (' + exposeAuthKey.length + ' chars)');
         }
 
-        // Query Ollama for available models
+        // Passthrough mode: forward from a remote /endpoint (Chutes, Groq, etc.)
+        var isPassthrough = args.passthrough === 'true';
+        var endpointAuth = args.endpoint_auth || '';
+        if (isPassthrough) {
+          dlog('expose: PASSTHROUGH mode \u2014 forwarding from upstream endpoint');
+        }
+
+        // Query models from the backend
         const ollamaUrl = args.ollama_url || process.env.OLLAMA_URL || 'http://localhost:11434';
         let models = [];
-        try {
-          const tagsResp = await fetch(ollamaUrl + '/api/tags');
-          if (tagsResp.ok) {
-            const tagsData = await tagsResp.json();
-            models = (tagsData.models || []).map(m => ({
-              name: m.name,
-              size: m.size || 0,
-              parameterSize: m.details?.parameter_size || '',
-              family: m.details?.family || '',
-              quantization: m.details?.quantization_level || '',
-            }));
+
+        if (isPassthrough) {
+          // Passthrough: query /v1/models from the upstream endpoint (OpenAI-compatible)
+          try {
+            var modelsHeaders = { 'Content-Type': 'application/json' };
+            if (endpointAuth) modelsHeaders['Authorization'] = 'Bearer ' + endpointAuth;
+            var modelsUrl = ollamaUrl.replace(/\\/+$/, '') + '/v1/models';
+            dlog('expose: passthrough querying models from ' + modelsUrl);
+            const modelsResp = await fetch(modelsUrl, { headers: modelsHeaders });
+            if (modelsResp.ok) {
+              const modelsData = await modelsResp.json();
+              var modelList = modelsData.data || modelsData.models || [];
+              models = modelList.map(function(m) {
+                return {
+                  name: m.id || m.name || 'unknown',
+                  size: 0,
+                  parameterSize: '',
+                  family: m.owned_by || '',
+                  quantization: '',
+                };
+              });
+            } else {
+              var errText = '';
+              try { errText = await modelsResp.text(); } catch {}
+              writeResp(id, { ok: false, output: 'Upstream /v1/models returned ' + modelsResp.status + ': ' + errText.slice(0, 200) });
+              return;
+            }
+          } catch (e) {
+            writeResp(id, { ok: false, output: 'Cannot reach upstream endpoint at ' + ollamaUrl + ': ' + e.message });
+            return;
+          }
+        } else {
+          // Local Ollama: query /api/tags
+          try {
+            const tagsResp = await fetch(ollamaUrl + '/api/tags');
+            if (tagsResp.ok) {
+              const tagsData = await tagsResp.json();
+              models = (tagsData.models || []).map(function(m) {
+                return {
+                  name: m.name,
+                  size: m.size || 0,
+                  parameterSize: m.details ? m.details.parameter_size || '' : '',
+                  family: m.details ? m.details.family || '' : '',
+                  quantization: m.details ? m.details.quantization_level || '' : '',
+                };
+              });
+            }
+          } catch (e) {
+            writeResp(id, { ok: false, output: 'Cannot reach Ollama at ' + ollamaUrl + ': ' + e.message });
+            return;
           }
-        } catch (e) {
-          writeResp(id, { ok: false, output: 'Cannot reach Ollama at ' + ollamaUrl + ': ' + e.message });
-          return;
         }
 
         if (models.length === 0) {
-          writeResp(id, { ok: false, output: 'No models found on Ollama. Pull a model first.' });
+          writeResp(id, { ok: false, output: isPassthrough ? 'No models found on upstream endpoint.' : 'No models found on Ollama. Pull a model first.' });
           return;
         }
+        dlog('expose: found ' + models.length + ' models' + (isPassthrough ? ' (passthrough)' : ''));
 
         // Fetch market rates from OpenRouter (free, no auth)
         let marketRates = {};
@@ -12782,10 +12826,12 @@ async function handleCmd(cmd) {
                   if (parsedReq.temperature !== undefined) chatBody.temperature = parsedReq.temperature;
                   if (parsedReq.max_tokens) chatBody.max_tokens = parsedReq.max_tokens;
 
-                  dlog('expose: calling /v1/chat/completions with ' + chatBody.messages.length + ' messages, tools=' + (chatBody.tools ? chatBody.tools.length : 0));
+                  var chatHeaders = { 'Content-Type': 'application/json' };
+                  if (isPassthrough && endpointAuth) chatHeaders['Authorization'] = 'Bearer ' + endpointAuth;
+                  dlog('expose: calling /v1/chat/completions with ' + chatBody.messages.length + ' messages, tools=' + (chatBody.tools ? chatBody.tools.length : 0) + (isPassthrough ? ' (passthrough)' : ''));
                   genResp = await fetch(ollamaUrl + '/v1/chat/completions', {
                     method: 'POST',
-                    headers: { 'Content-Type': 'application/json' },
+                    headers: chatHeaders,
                     body: JSON.stringify(chatBody),
                   });
                   genData = await genResp.json();
@@ -12816,8 +12862,36 @@ async function handleCmd(cmd) {
                     usage: { input_tokens: inputTokens, output_tokens: outputTokens },
                     pricing: entry.pricing,
                   };
+                } else if (isPassthrough) {
+                  // Passthrough flat prompt \u2014 convert to /v1/chat/completions (upstream has no /api/generate)
+                  var flatPrompt = parsedReq && parsedReq.prompt ? parsedReq.prompt : (prompt || 'Hello');
+                  var ptHeaders = { 'Content-Type': 'application/json' };
+                  if (endpointAuth) ptHeaders['Authorization'] = 'Bearer ' + endpointAuth;
+                  genResp = await fetch(ollamaUrl + '/v1/chat/completions', {
+                    method: 'POST',
+                    headers: ptHeaders,
+                    body: JSON.stringify({
+                      model: model.name,
+                      messages: [{ role: 'user', content: flatPrompt }],
+                      stream: false,
+                    }),
+                  });
+                  genData = await genResp.json();
+                  var ptChoices = genData.choices || [];
+                  var ptMsg = (ptChoices[0] || {}).message || {};
+                  output = (ptMsg.content || '').replace(/<think>[\\s\\S]*?<\\/think>/g, '').trim();
+                  inputTokens = (genData.usage || {}).prompt_tokens || 0;
+                  outputTokens = (genData.usage || {}).completion_tokens || 0;
+
+                  responsePayload = {
+                    model: model.name,
+                    response: output,
+                    choices: ptChoices,
+                    usage: { input_tokens: inputTokens, output_tokens: outputTokens },
+                    pricing: entry.pricing,
+                  };
                 } else {
-                  // Flat prompt \u2014 use /api/generate (original behavior)
+                  // Flat prompt \u2014 use /api/generate (local Ollama)
                   var flatPrompt = parsedReq && parsedReq.prompt ? parsedReq.prompt : (prompt || 'Hello');
                   genResp = await fetch(ollamaUrl + '/api/generate', {
                     method: 'POST',
@@ -28358,6 +28432,7 @@ ${this.formatConnectionInfo()}`);
       _margin;
       _passthrough = false;
       _loadbalance = false;
+      _endpointAuth;
       _pollTimer = null;
       _stats = {
         status: "standby",
@@ -28402,6 +28477,7 @@ ${this.formatConnectionInfo()}`);
         this._margin = options.margin ?? 0.5;
         this._passthrough = options.passthrough ?? false;
         this._loadbalance = options.loadbalance ?? false;
+        this._endpointAuth = options.endpointAuth;
         this._onInfo = options.onInfo;
         this._onError = options.onError;
         if (options.authKey === void 0 || options.authKey === "") {
@@ -28421,21 +28497,23 @@ ${this.formatConnectionInfo()}`);
           throw new Error(`Nexus daemon connect failed: ${connectResult.error}`);
         }
         await new Promise((r) => setTimeout(r, 500));
-        this._onInfo?.("Registering inference capabilities...");
-        let exposeResult = await this._nexusTool.execute({
+        this._onInfo?.(this._passthrough ? `Registering passthrough capabilities (\u2192 ${this._targetUrl})...` : "Registering inference capabilities...");
+        const exposeArgs = {
           action: "expose",
           ollama_url: this._targetUrl,
           margin: String(this._margin),
           auth_key: this._authKey
-        });
+        };
+        if (this._passthrough) {
+          exposeArgs.passthrough = "true";
+          if (this._endpointAuth) {
+            exposeArgs.endpoint_auth = this._endpointAuth;
+          }
+        }
+        let exposeResult = await this._nexusTool.execute(exposeArgs);
         if (!exposeResult.success && exposeResult.error?.includes("not running")) {
           await new Promise((r) => setTimeout(r, 1500));
-          exposeResult = await this._nexusTool.execute({
-            action: "expose",
-            ollama_url: this._targetUrl,
-            margin: String(this._margin),
-            auth_key: this._authKey
-          });
+          exposeResult = await this._nexusTool.execute(exposeArgs);
         }
         if (!exposeResult.success) {
           throw new Error(`Expose failed: ${exposeResult.error}`);
@@ -46917,6 +46995,7 @@ Respond concisely and safely. Remember: you are talking to the general public.`;
           stateDir: join50(repoRoot, ".oa"),
           passthrough: passthrough ?? false,
           loadbalance: loadbalance ?? false,
+          endpointAuth: passthrough ? config.apiKey : void 0,
           onInfo: (msg) => {
             exposeSpinnerMsg = msg;
           },

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "open-agents-ai",
-  "version": "0.103.37",
+  "version": "0.103.38",
   "description": "AI coding agent powered by open-source models (Ollama/vLLM) — interactive TUI with agentic tool-calling loop",
   "type": "module",
   "main": "./dist/index.js",