agentram 0.1.7 → 0.1.9

package/agentram/cli.py

@@ -825,6 +825,8 @@ def model_error_hint(message: str) -> str:
         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:

package/agentram/orchestration.py

@@ -4,6 +4,7 @@ from concurrent.futures import ThreadPoolExecutor, as_completed
 from dataclasses import dataclass, field
 import json
 import os
+import re
 import shlex
 import subprocess
 import urllib.error
@@ -139,6 +140,9 @@ class MultiModelCodingOrchestrator:
         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", ""))
 
@@ -188,3 +192,38 @@ 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 strip_thinking_blocks("".join(parts)).strip()
+
+def strip_thinking_blocks(text: str) -> str:
+    text = re.sub(r"<thinking>.*?</thinking>", "", text, flags=re.DOTALL | re.IGNORECASE)
+    text = re.sub(r"<think>.*?</think>", "", text, flags=re.DOTALL | re.IGNORECASE)
+    text = re.sub(r"^\s*</?(thinking|think)>\s*", "", text, flags=re.IGNORECASE)
+    return text.strip()

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "agentram",
-  "version": "0.1.7",
+  "version": "0.1.9",
   "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 = "0.1.7"
+version = "0.1.9"
 description = "Async, model-agnostic RAM layer for agentic coding tools."
 readme = "README.md"
 license = "MIT"