open-agents-ai 0.185.88 → 0.185.90

package/README.md

@@ -610,6 +610,12 @@ curl -X DELETE -H "Authorization: Bearer $ADMIN_KEY" \
 | GET | `/v1/models` | read | List models (OpenAI format) |
 | POST | `/v1/chat/completions` | run | Chat inference (stream + sync) |
 | POST | `/v1/embeddings` | run | Generate embeddings |
+| POST | `/v1/chat` | run | Stateful chat with full tool access (sessions, context, memory) |
+| GET | `/v1/chat/sessions` | read | List active chat sessions |
+| GET | `/v1/system` | none | GPU/RAM/CPU info + model recommendations |
+| GET | `/v1/audit` | read | Query audit log (since, user, limit filters) |
+| GET | `/openapi.json` | none | OpenAPI 3.0 specification |
+| GET | `/docs` | none | Swagger UI (interactive API docs) |
 | POST | `/v1/run` | run | Submit agentic task |
 | GET | `/v1/runs` | read | List all runs |
 | GET | `/v1/runs/:id` | read | Run status |
@@ -627,6 +633,55 @@ curl -X DELETE -H "Authorization: Bearer $ADMIN_KEY" \
 | POST | `/v1/profiles` | admin | Create/update profile (password field for encryption) |
 | DELETE | `/v1/profiles/:name` | admin | Delete custom profile |
 
+#### Stateful Chat — `/v1/chat`
+
+Unlike `/v1/chat/completions` (raw Ollama proxy), `/v1/chat` spawns the full OA agent with all 61 tools for each message. The agent can search the web, read files, run shell commands, and use memory — exactly like the TUI.
+
+```bash
+# Send a chat message (full tool access)
+curl -s http://localhost:11435/v1/chat \
+  -H "Content-Type: application/json" \
+  -d '{"message": "What is happening in the world today?", "model": "qwen3.5:9b", "stream": false}'
+
+# Response: {"session_id": "abc123", "message": {"role": "assistant", "content": "..."}}
+```
+
+**Session management:** Each chat message returns a `session_id`. Send it back to maintain conversation context across turns:
+
+```bash
+curl -s http://localhost:11435/v1/chat \
+  -d '{"session_id": "abc123", "message": "Tell me more about that", "model": "qwen3.5:9b", "stream": false}'
+```
+
+Sessions expire after 30 minutes of inactivity. List active sessions: `GET /v1/chat/sessions`.
+
+**Streaming:** Set `"stream": true` for Server-Sent Events with tool call visualization and incremental content.
+
+#### Web Interface
+
+Open `http://localhost:11435/` in a browser when `oa serve` is running. Zero external dependencies — single self-contained HTML page.
+
+**Tabs:**
+- **Chat** — Conversational interface using `/v1/chat` with full tool access, session persistence, streaming responses, and collapsible tool call dropdowns
+- **Agent** — Submit agentic tasks via `/v1/run`, profile selection, live SSE event stream, abort button
+- **Dashboard** — System health (GPU, RAM, uptime), per-provider token usage (persistent across restarts), active process monitor, job history with pagination
+- **Config** — Server settings table, model switcher, endpoint manager (add/change inference providers), profile list
+- **Activity** — Real-time audit log feed with color-coded status codes
+
+**Design:** Dark theme (#1a1a1e background, #b2920a gold accent, SF Mono font) matching the TUI and /call voice interface. Mobile responsive with CSS media queries.
+
+**Features:**
+- Model picker populated from `/v1/models`
+- API key support (stored in localStorage)
+- System prompt (collapsible textarea)
+- Markdown rendering with code block copy buttons
+- Docker sandbox toggle (native vs container execution)
+- Workspace sidebar (toggleable file tree)
+- Token counter per conversation
+- Conversation export (Markdown or JSON)
+- GPU/VRAM detection with model compatibility recommendations
+- Per-provider token tracking (persisted to `.oa/usage/token-usage.json`)
+
 ### Enterprise Licensing
 
 Free for non-commercial use under CC-BY-NC-4.0. For enterprise/commercial licensing, contact [zoomerconsulting.com](https://zoomerconsulting.com).

package/dist/index.js

@@ -68133,22 +68133,26 @@ Respond conversationally. Call task_complete with your final response.`;
         });
         await new Promise((resolve36) => child.on("close", resolve36));
         let content = "";
-        let summaryContent = "";
-        for (const line of output.split("\n")) {
-          if (!line.trim())
-            continue;
-          try {
-            const evt = JSON.parse(line);
-            if (evt.status === "completed" || evt.status === "failed") {
-              const summary = evt.summary || "";
-              const match = summary.match(/Tokens:\s*[\d,]+\s+([\s\S]*)/);
-              content = match ? match[1].trim() : summary;
+        try {
+          const result = JSON.parse(output.trim());
+          const summary = result.summary || "";
+          const match = summary.match(/Tokens:\s*[\d,]+\s+([\s\S]*)/);
+          content = match ? match[1].trim() : summary;
+        } catch {
+          for (const line of output.split("\n")) {
+            if (!line.trim())
+              continue;
+            try {
+              const evt = JSON.parse(line);
+              if (evt.status === "completed") {
+                const summary = evt.summary || "";
+                const match = summary.match(/Tokens:\s*[\d,]+\s+([\s\S]*)/);
+                content = match ? match[1].trim() : summary;
+              }
+            } catch {
             }
-          } catch {
           }
         }
-        if (!content.trim())
-          content = summaryContent;
         addAssistantMessage(session, content.trim());
         jsonResponse(res, 200, {
           session_id: session.id,

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "open-agents-ai",
-  "version": "0.185.88",
+  "version": "0.185.90",
   "description": "AI coding agent powered by open-source models (Ollama/vLLM) — interactive TUI with agentic tool-calling loop",
   "type": "module",
   "main": "./dist/index.js",