agentram 0.1.6 → 0.1.8

package/agentram/cli.py

@@ -660,7 +660,7 @@ def supervisor_workflow_text(context: McpContext, prompt: str) -> str:
             try:
                 outputs[slot] = future.result()
             except Exception as error:  # noqa: BLE001 - agent boundary
-                outputs[slot] = f"error: {error}"
+                outputs[slot] = f"error: {model_error_hint(str(error))}"
     if not main_agent:
         outputs["main"] = "No main agent bound. Use /bind-agent main <provider> <model>."
     if small_agent and outputs.get("small") and not outputs["small"].startswith("error:"):
@@ -821,10 +821,16 @@ def model_error_hint(message: str) -> str:
     lower = message.lower()
     if "base_url is required" in lower:
         return message + " | Fix: /remove-model <id> or re-bind with --base-url http://localhost:8000/v1"
-    if "actively refused" in lower or "connection refused" in lower or "winerror 10061" in lower:
-        return message + " | Fix: start your OpenAI-compatible server at base_url, or change --base-url."
-    if "missing api key env" in lower:
-        return message + " | Fix: set environment variable, then bind using --api-key-env ENV_NAME, not raw key."
+    if "actively refused" in lower or "connection refused" in lower or "winerror 10061" in lower:
+        return message + " | Fix: start your OpenAI-compatible server at base_url, or change --base-url."
+    if "http 404" in lower or "404: not found" in lower:
+        return message + " | Fix: verify base_url includes /v1, provider supports /chat/completions, and model name exists."
+    if "http 400" in lower and "not supported" in lower:
+        return message + " | Fix: this account/provider rejects that model. Bind a supported model name from your local endpoint."
+    if "returned non-json" in lower or "expecting value" in lower:
+        return message + " | Fix: endpoint returned empty/HTML/non-JSON. Check base_url, auth key, proxy, and server logs."
+    if "missing api key env" in lower:
+        return message + " | Fix: set environment variable, then bind using --api-key-env ENV_NAME, not raw key."
     return message
 
 def claude_template_root() -> Path:

package/agentram/orchestration.py

@@ -6,6 +6,7 @@ import json
 import os
 import shlex
 import subprocess
+import urllib.error
 import urllib.request
 from typing import Any, Callable
 from uuid import uuid4
@@ -125,8 +126,23 @@ class MultiModelCodingOrchestrator:
             headers={"Content-Type": "application/json", "Authorization": f"Bearer {api_key}"} if api_key else {"Content-Type": "application/json"},
             method="POST",
         )
-        with urllib.request.urlopen(request, timeout=120) as response:
-            data = json.loads(response.read().decode("utf-8"))
+        url = endpoint.base_url.rstrip("/") + "/chat/completions"
+        try:
+            with urllib.request.urlopen(request, timeout=120) as response:
+                raw = response.read().decode("utf-8")
+        except urllib.error.HTTPError as error:
+            body = error.read().decode("utf-8", errors="replace") if error.fp else ""
+            hint = f"OpenAI-compatible HTTP {error.code} at {url}"
+            if error.code == 404:
+                hint += " | base_url should include /v1 but not /chat/completions; verify provider URL and model name"
+            raise RuntimeError(f"{hint} | response={body[:500]}") from error
+        try:
+            data = json.loads(raw)
+        except json.JSONDecodeError as error:
+            streamed = parse_openai_sse(raw)
+            if streamed:
+                return streamed
+            raise RuntimeError(f"OpenAI-compatible returned non-JSON at {url} | response={raw[:500]}") from error
         return str(data.get("choices", [{}])[0].get("message", {}).get("content", ""))
 
     def _call_anthropic(self, endpoint: AgentModelEndpoint, prompt: str) -> str:
@@ -175,3 +191,32 @@ class MultiModelCodingOrchestrator:
         if process.returncode != 0:
             raise RuntimeError(error or f"claude command failed with exit code {process.returncode}")
         return output or error
+
+def parse_openai_sse(raw: str) -> str:
+    parts: list[str] = []
+    for line in raw.splitlines():
+        stripped = line.strip()
+        if not stripped.startswith("data:"):
+            continue
+        payload = stripped[5:].strip()
+        if not payload or payload == "[DONE]":
+            continue
+        try:
+            item = json.loads(payload)
+        except json.JSONDecodeError:
+            continue
+        choices = item.get("choices", [])
+        if not choices or not isinstance(choices, list):
+            continue
+        choice = choices[0]
+        if not isinstance(choice, dict):
+            continue
+        delta = choice.get("delta", {})
+        if isinstance(delta, dict):
+            content = delta.get("content")
+            if content:
+                parts.append(str(content))
+        message = choice.get("message", {})
+        if isinstance(message, dict) and message.get("content"):
+            parts.append(str(message.get("content")))
+    return "".join(parts).strip()

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "agentram",
-  "version": "0.1.6",
+  "version": "0.1.8",
   "description": "Async, model-agnostic Working RAM for coding agents.",
   "license": "MIT",
   "homepage": "https://github.com/trancongnghia/AGENT_RAM#readme",

package/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "agentram"
-version = "0.1.6"
+version = "0.1.8"
 description = "Async, model-agnostic RAM layer for agentic coding tools."
 readme = "README.md"
 license = "MIT"