omni-ai-cli 1.1.0 → 1.2.0

package/README.md

@@ -543,7 +543,6 @@ guardar nem rotacionar.
   arquivos. Os agentes não editam o projeto ao mesmo tempo.
 - A classificação simples/complexa é por palavras-chave e tamanho, não por um modelo.
 - Trocar de modelo não renova a cota da conta.
-- O OpenRouter não tem streaming nesta versão: a resposta aparece inteira no final.
 - No Windows, o código usa os equivalentes nativos (grupo de processos e `taskkill`, `msvcrt`, junções de pasta), mas foi testado de verdade só no macOS.
 
 ---

package/docs/README.en.md

@@ -542,7 +542,6 @@ The workflow already requests `id-token: write` and `NPM_CONFIG_PROVENANCE`; the
   access the files. The agents do not edit the project at the same time.
 - The simple/complex classification is by keywords and length, not by a model.
 - Switching models does not renew the account's quota.
-- OpenRouter has no streaming in this version: the answer appears whole at the end.
 - On Windows the code uses the native equivalents (process groups and `taskkill`, `msvcrt`, folder junctions), but it has only been tested for real on macOS.
 
 ---

package/docs/README.es.md

@@ -545,7 +545,6 @@ guardar ni rotar.
   a los archivos. Los agentes no editan el proyecto al mismo tiempo.
 - La clasificación simple/compleja se hace por palabras clave y tamaño, no con un modelo.
 - Cambiar de modelo no renueva la cuota de la cuenta.
-- OpenRouter no tiene streaming en esta versión: la respuesta aparece completa al final.
 - En Windows el código usa los equivalentes nativos (grupos de procesos y `taskkill`, `msvcrt`, uniones de carpeta), pero solo se probó de verdad en macOS.
 
 ---

package/docs/README.fr.md

@@ -555,8 +555,6 @@ Le workflow demande déjà `id-token: write` et `NPM_CONFIG_PROVENANCE` ; il n'y
 - La classification simple/complexe repose sur des mots-clés et la taille, pas sur un
   modèle.
 - Changer de modèle ne renouvelle pas le quota du compte.
-- OpenRouter n'a pas de streaming dans cette version : la réponse apparaît en entier à
-  la fin.
 - Sous Windows le code utilise les équivalents natifs (groupes de processus et `taskkill`, `msvcrt`, jonctions de dossier), mais il n'a été testé pour de vrai que sous macOS.
 
 ---

package/omni_ai/chat.py

@@ -154,6 +154,7 @@ T = {
 /account [list|add|login|remove] [codex|agy|grok] NOME  Contas (Claude por padrão; quantas quiser)
 /key [add|remove] [{keys}] [NOME] Chaves de API (várias por ferramenta, usadas em ordem)
 /status   /reset                         Status das contas / zerar cooldowns
+/doctor                                 Diagnóstico de instalação, contas e chaves
 /sync [--dry-run]                        Compartilhar MCPs e skills entre Claude, Codex e agy
 /mode default|plan|edits|auto|yolo      Modo de permissão (vale para Claude, Codex e agy)
 /setup [install]                         Guia de primeiro acesso; install instala as ferramentas que faltam
@@ -177,6 +178,7 @@ T = {
 /account [list|add|login|remove] [codex|agy|grok] NAME  Accounts (Claude by default; as many as you want)
 /key [add|remove] [{keys}] [NAME] API keys (several per tool, tried in order)
 /status   /reset                         Account status / clear cooldowns
+/doctor                                 Diagnose install, accounts and keys
 /sync [--dry-run]                        Share MCPs and skills across Claude, Codex and agy
 /mode default|plan|edits|auto|yolo      Permission mode (applies to Claude, Codex and agy)
 /setup [install]                         First-run guide; install installs the missing tools
@@ -200,6 +202,7 @@ T = {
 /account [list|add|login|remove] [codex|agy|grok] NOMBRE  Cuentas (Claude por defecto; las que quieras)
 /key [add|remove] [{keys}] [NOMBRE] Claves de API (varias por herramienta, en orden)
 /status   /reset                         Estado de cuentas / limpiar cooldowns
+/doctor                                 Diagnóstico de instalación, cuentas y claves
 /sync [--dry-run]                        Compartir MCPs y skills entre Claude, Codex y agy
 /mode default|plan|edits|auto|yolo      Modo de permisos (Claude, Codex y agy)
 /setup [install]                         Guía de primer acceso; install instala las herramientas que faltan
@@ -223,6 +226,7 @@ T = {
 /account [list|add|login|remove] [codex|agy|grok] NOM  Comptes (Claude par défaut ; autant que voulu)
 /key [add|remove] [{keys}] [NOM] Clés API (plusieurs par outil, essayées dans l'ordre)
 /status   /reset                         État des comptes / réinitialiser les cooldowns
+/doctor                                 Diagnostic installation, comptes et clés
 /sync [--dry-run]                        Partager MCP et skills entre Claude, Codex et agy
 /mode default|plan|edits|auto|yolo      Mode de permissions (Claude, Codex et agy)
 /setup [install]                         Guide de démarrage ; install installe les outils manquants
@@ -477,10 +481,24 @@ class Runner:
             if job.get('dispatches'):
                 job['dispatches'][-1]['sent'] = event['data']
             view.note('dados pessoais mascarados antes do envio · /sent para ver')
+        elif kind == 'smart.delta':
+            # Stream the answer line by line as the tokens arrive (OpenRouter).
+            job['stream_buf'] = job.get('stream_buf', '') + event.get('text', '')
+            job['streamed'] = True
+            while '\n' in job['stream_buf']:
+                line, job['stream_buf'] = job['stream_buf'].split('\n', 1)
+                view.stream_line(line)
         elif kind == 'smart.answer':
             job['model'] = event.get('model')
             spend(job, event.get('usage') or {})
-            self.answer(job, event.get('content', ''))
+            if job.get('streamed'):
+                if job.get('stream_buf'):
+                    view.stream_line(job['stream_buf'])
+                    job['stream_buf'] = ''
+                # the streamed lines were display-only; keep the full, unmasked answer for the session
+                job['answers'] = [event.get('content', '')]
+            else:
+                self.answer(job, event.get('content', ''))
             view.note('modelo: ' + str(event.get('model', '?')))
         elif kind in ('item.started', 'item.completed'):
             item = event.get('item', {})
@@ -1016,7 +1034,7 @@ def compact(session):
 
 
 TOOL_COMMANDS = {'/usage': ['--usage'], '/limits': ['--usage'], '/model': ['--model'], '/account': ['--account'], '/key': ['--key'],
-                 '/status': ['--status'], '/sync': ['--sync'], '/update': ['--update'], '/reset': ['--reset']}
+                 '/status': ['--status'], '/doctor': ['--doctor'], '/sync': ['--sync'], '/update': ['--update'], '/reset': ['--reset']}
 
 
 def run_tool(args):
@@ -1027,7 +1045,7 @@ def run_tool(args):
         pass
 
 
-BUILTIN = ['/usage', '/clear', '/compact', '/queue', '/versions', '/setup', '/terminal-setup', '/tool', '/model', '/account', '/key', '/status', '/reset', '/sync', '/update', '/mode', '/lang',
+BUILTIN = ['/usage', '/clear', '/compact', '/queue', '/versions', '/setup', '/terminal-setup', '/tool', '/model', '/account', '/key', '/status', '/doctor', '/reset', '/sync', '/update', '/mode', '/lang',
            '/skills', '/history', '/sent', '/trace', '/sessions', '/resume', '/new', '/parallel', '/help', '/exit']
 
 

package/omni_ai/openrouter.py

@@ -105,6 +105,55 @@ class OpenRouterClient:
         except urllib.error.URLError as e:
             raise RuntimeError("Falha de rede ao acessar OpenRouter") from None
 
+    def _stream_request(self, data: dict):
+        """POST /chat/completions with stream=True, yielding ('delta', text) per token and a final
+        ('final', {content, model, usage}). Raises RuntimeError on any failure, like _request."""
+        if os.environ.get('SMART_AI_EVENTS') == '1':
+            print(json.dumps({'type': 'smart.request', 'data': data}, ensure_ascii=False), file=sys.stderr, flush=True)
+        headers = {
+            "Content-Type": "application/json",
+            "HTTP-Referer": "https://github.com/samuelrms/omni-ai-cli",
+            "X-Title": "Omni AI CLI",
+            "Accept": "text/event-stream",
+        }
+        if self.api_key:
+            headers["Authorization"] = f"Bearer {self.api_key}"
+        body = json.dumps(dict(data, stream=True, stream_options={"include_usage": True})).encode()
+        req = urllib.request.Request(f"{OPENROUTER_BASE}/chat/completions", data=body, headers=headers, method="POST")
+        content, model, usage = [], None, {}
+        try:
+            with urllib.request.urlopen(req, timeout=60) as resp:
+                for raw in resp:
+                    line = raw.decode("utf-8", "replace").strip()
+                    if not line.startswith("data:"):
+                        continue
+                    payload = line[5:].strip()
+                    if payload == "[DONE]":
+                        break
+                    try:
+                        chunk = json.loads(payload)
+                    except ValueError:
+                        continue
+                    model = chunk.get("model") or model
+                    usage = chunk.get("usage") or usage
+                    for choice in chunk.get("choices", []):
+                        piece = (choice.get("delta") or {}).get("content") or ""
+                        if piece:
+                            content.append(piece)
+                            yield ("delta", piece)
+        except urllib.error.HTTPError as e:
+            try:
+                reason = json.loads(e.read().decode())["error"]["message"][:160]
+            except (ValueError, KeyError, TypeError, OSError):
+                reason = ""
+            e.close()
+            raise RuntimeError(f"OpenRouter HTTP {e.code}" + (f": {reason}" if reason else "")) from None
+        except (ValueError, TimeoutError):
+            raise RuntimeError("Resposta inválida ou timeout do OpenRouter") from None
+        except urllib.error.URLError:
+            raise RuntimeError("Falha de rede ao acessar OpenRouter") from None
+        yield ("final", {"content": "".join(content), "model": model, "usage": usage})
+
     def list_free_models(self) -> list:
         """Lista todos os modelos gratuitos disponíveis."""
         resp = self._request("/models")
@@ -122,6 +171,7 @@ class OpenRouterClient:
         system_prompt: str = None,
         temperature: float = 0.7,
         max_tokens: int = 4096,
+        on_delta=None,
     ) -> dict:
         """
         Envia um prompt e retorna a resposta.
@@ -185,10 +235,26 @@ class OpenRouterClient:
             if not self.allow_paid:
                 data["provider"] = {"max_price": {"prompt": 0, "completion": 0}}
             try:
-                resp = self._request("/chat/completions", data=data, method="POST")
-                if resp.get("choices"):
-                    break
-                last_error = RuntimeError("OpenRouter não retornou uma resposta válida")
+                if on_delta is not None:
+                    # Stream the tokens as they arrive; a chunk may still be a masked placeholder, so
+                    # unmask each piece best-effort and unmask the whole answer again at the end.
+                    final = None
+                    for kind, payload in self._stream_request(data):
+                        if kind == "delta":
+                            piece = self.masker.unmask(payload, self._pii_map) if (self.masker and self._pii_map) else payload
+                            on_delta(piece)
+                        else:
+                            final = payload
+                    if final and final["content"].strip():
+                        resp = {"choices": [{"message": {"content": final["content"]}}],
+                                "model": final["model"], "usage": final["usage"]}
+                        break
+                    last_error = RuntimeError("OpenRouter não retornou uma resposta válida")
+                else:
+                    resp = self._request("/chat/completions", data=data, method="POST")
+                    if resp.get("choices"):
+                        break
+                    last_error = RuntimeError("OpenRouter não retornou uma resposta válida")
             except RuntimeError as error:
                 last_error = error
                 # Bad key or no credit: another model won't help
@@ -310,19 +376,31 @@ def main():
             parser.print_help()
             sys.exit(1)
 
+    events = os.environ.get('SMART_AI_EVENTS') == '1'
+    # Stream tokens for the chat (events) and for a human at a terminal; keep --json buffered.
+    if events:
+        on_delta = lambda piece: print(json.dumps({'type': 'smart.delta', 'text': piece}, ensure_ascii=False), flush=True)
+    elif not args.json:
+        on_delta = lambda piece: (sys.stdout.write(piece), sys.stdout.flush())
+    else:
+        on_delta = None
+
     try:
         result = client.chat(
             prompt=prompt,
             system_prompt=args.system,
             temperature=args.temperature,
+            on_delta=on_delta,
         )
 
-        if os.environ.get('SMART_AI_EVENTS') == '1':
+        if events:
             print(json.dumps({'type': 'smart.answer', **result}, ensure_ascii=False), flush=True)
         elif args.json:
             print(json.dumps(result, indent=2, ensure_ascii=False))
-        else:
+        elif on_delta is None:
             print(result["content"])
+        else:
+            print()  # end the streamed line
 
     except RuntimeError as e:
         print(f"❌ Erro: {e}", file=sys.stderr)

package/omni_ai/ui.py

@@ -214,10 +214,20 @@ class View:
     def __init__(self, prefix=''):
         self.prefix = prefix
         self.pending = None  # last action, so its result can be attached under it
+        self._streamed = False  # whether a streaming answer has started printing
 
     def _p(self, text):
         out('\n'.join(self.prefix + line for line in text.split('\n')))
 
+    def stream_line(self, line):
+        """One completed line of a streaming answer, printed as it arrives (line-granular keeps the
+        chat's input box intact, unlike raw partial writes). The first line carries the answer mark."""
+        if not self._streamed:
+            self._p('\n' + gradient(MARK) + ' ' + line)
+            self._streamed = True
+        else:
+            self._p('  ' + line)
+
     def provider(self, tool, detail):
         self._p(dim('  ') + rgb(TOOL_RGB.get(tool, (6, 182, 212)), '● ' + tool) + (dim(' · ' + detail) if detail else ''))
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "omni-ai-cli",
-  "version": "1.1.0",
+  "version": "1.2.0",
   "description": "One chat for Claude Code, Codex, Antigravity and OpenRouter, with automatic routing, account fallback, API keys, permission modes and MCP/skill sync.",
   "bin": {
     "ai": "bin/ai.js",