programasweights 0.2.3__tar.gz → 0.2.4__tar.gz

{programasweights-0.2.3 → programasweights-0.2.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: programasweights
-Version: 0.2.3
+Version: 0.2.4
 Summary: Compile natural language specifications into neural programs that run locally via llama.cpp.
 Project-URL: Homepage, https://programasweights.com
 Project-URL: Repository, https://github.com/programasweights/programasweights-python

{programasweights-0.2.3 → programasweights-0.2.4}/programasweights/__init__.py

@@ -23,7 +23,7 @@ API reference:
 """
 from __future__ import annotations
 
-__version__ = "0.2.3"
+__version__ = "0.2.4"
 
 from .config import get_api_url, get_api_key, set_api_key
 

{programasweights-0.2.3 → programasweights-0.2.4}/programasweights/client.py

@@ -108,25 +108,38 @@ class PAWClient:
         """Download a .paw bundle to the local cache.
 
         Returns the path to the extracted program directory.
-        Retries on 404 since freshly compiled programs may still be uploading.
+        Handles 202 Accepted (assets still generating) and 302 redirects (HF CDN).
         """
         program_dir = config.get_programs_dir() / program_id
         if (program_dir / "prompt_template.txt").exists():
             return program_dir
 
-        max_retries = 10
-        for attempt in range(max_retries):
+        max_wait = 30
+        elapsed = 0
+        resp = None
+        while elapsed < max_wait:
             resp = httpx.get(
                 f"{self._api_url}/api/v1/programs/{program_id}/download",
                 headers=self._headers(),
                 timeout=60.0,
                 follow_redirects=True,
             )
-            if resp.status_code == 404 and attempt < max_retries - 1:
+            if resp.status_code == 202:
+                retry_after = int(resp.headers.get("Retry-After", "3"))
+                time.sleep(retry_after)
+                elapsed += retry_after
+                continue
+            if resp.status_code == 404 and elapsed < max_wait - 3:
                 time.sleep(3)
+                elapsed += 3
                 continue
             resp.raise_for_status()
             break
+        else:
+            raise RuntimeError(
+                f"Program {program_id} assets not ready after {max_wait}s. "
+                "The program may still be generating. Try again shortly."
+            )
 
         program_dir.mkdir(parents=True, exist_ok=True)
         paw_path = program_dir / f"{program_id}.paw"

{programasweights-0.2.3 → programasweights-0.2.4}/programasweights/runtime_llamacpp.py

@@ -67,24 +67,24 @@ class PawFunction:
                 n_gpu_layers=n_gpu_layers,
                 verbose=verbose,
             )
+
+            adapter_path = program_dir / "adapter.gguf"
+            if adapter_path.exists():
+                self._adapter = llama_cpp.llama_adapter_lora_init(
+                    self._llm.model, str(adapter_path).encode("utf-8"),
+                )
+                if self._adapter:
+                    llama_cpp.llama_set_adapter_lora(self._llm.ctx, self._adapter, 1.0)
+                else:
+                    raise RuntimeError(f"Failed to load LoRA adapter: {adapter_path}")
+            else:
+                self._adapter = None
         finally:
             if not verbose:
                 _os.dup2(_old_stderr, _stderr_fd)
                 _os.close(_devnull)
                 _os.close(_old_stderr)
 
-        adapter_path = program_dir / "adapter.gguf"
-        if adapter_path.exists():
-            self._adapter = llama_cpp.llama_adapter_lora_init(
-                self._llm.model, str(adapter_path).encode("utf-8"),
-            )
-            if self._adapter:
-                llama_cpp.llama_set_adapter_lora(self._llm.ctx, self._adapter, 1.0)
-            else:
-                raise RuntimeError(f"Failed to load LoRA adapter: {adapter_path}")
-        else:
-            self._adapter = None
-
         placeholder = "{INPUT_PLACEHOLDER}"
         self._use_special = interpreter not in ("gpt2",)
 

{programasweights-0.2.3 → programasweights-0.2.4}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "programasweights"
-version = "0.2.3"
+version = "0.2.4"
 description = "Compile natural language specifications into neural programs that run locally via llama.cpp."
 readme = "PYPI_README.md"
 requires-python = ">=3.9"

{programasweights-0.2.3 → programasweights-0.2.4}/server/api/routes/compile.py

@@ -140,7 +140,7 @@ async def submit_compile(
                 public=req.public,
                 name=req.name,
                 tags=req.tags,
-                hf_url=f"https://huggingface.co/programasweights/paw-programs/resolve/main/{pid}.paw",
+                hf_url=None,
             ))
 
         db.add(CompileLog(

{programasweights-0.2.3 → programasweights-0.2.4}/server/api/routes/programs.py

@@ -6,7 +6,7 @@ import re
 from pathlib import Path
 
 from fastapi import APIRouter, Depends, HTTPException, Request
-from fastapi.responses import FileResponse, RedirectResponse
+from fastapi.responses import FileResponse, JSONResponse, RedirectResponse
 
 from api.config import get_settings
 from sqlalchemy import func, select, or_
@@ -414,6 +414,10 @@ async def download_program(
     program.downloads = (program.downloads or 0) + 1
     await db.commit()
 
+    if program.hf_url:
+        hf_url = f"https://huggingface.co/programasweights/paw-programs/resolve/main/{program.id}.paw"
+        return RedirectResponse(url=hf_url, status_code=302)
+
     settings = get_settings()
     local_paw = Path(settings.STORAGE_PATH) / program.id / f"{program.id}.paw"
     if local_paw.exists():
@@ -423,8 +427,11 @@ async def download_program(
             filename=f"{program.id}.paw",
         )
 
-    hf_url = f"https://huggingface.co/programasweights/paw-programs/resolve/main/{program.id}.paw"
-    return RedirectResponse(url=hf_url, status_code=302)
+    return JSONResponse(
+        status_code=202,
+        content={"status": "generating", "message": "Program assets are being prepared. Retry shortly."},
+        headers={"Retry-After": "3"},
+    )
 
 
 ALLOWED_ASSETS = {"adapter.gguf", "prompt_template.txt", "prefix_cache.bin", "prefix_tokens.json"}
@@ -443,18 +450,25 @@ async def serve_program_asset(
     if not program:
         raise HTTPException(status_code=404, detail="Asset not found")
 
+    if program.hf_url:
+        hf_url = f"https://huggingface.co/programasweights/paw-programs/resolve/main/{program.id}/{filename}"
+        return RedirectResponse(url=hf_url, status_code=302)
+
     settings = get_settings()
     asset_path = Path(settings.STORAGE_PATH) / program.id / filename
-    if not asset_path.exists():
-        raise HTTPException(status_code=404, detail="Asset not found on this server")
-
-    media_type = "application/octet-stream"
-    if filename.endswith(".txt"):
-        media_type = "text/plain"
-    elif filename.endswith(".json"):
-        media_type = "application/json"
-
-    return FileResponse(path=str(asset_path), media_type=media_type, filename=filename)
+    if asset_path.exists():
+        media_type = "application/octet-stream"
+        if filename.endswith(".txt"):
+            media_type = "text/plain"
+        elif filename.endswith(".json"):
+            media_type = "application/json"
+        return FileResponse(path=str(asset_path), media_type=media_type, filename=filename)
+
+    return JSONResponse(
+        status_code=202,
+        content={"status": "generating", "message": "Program assets are being prepared. Retry shortly."},
+        headers={"Retry-After": "3"},
+    )
 
 
 # --- Update program ---

{programasweights-0.2.3 → programasweights-0.2.4}/server/api/services/compile_provider.py

@@ -509,10 +509,22 @@ class CompileProvider:
                     upload_all_to_hf, program_id, adapter_dir,
                     self.interpreter, paw_path,
                 )
-                logger.info("hf_upload_done", program_id=program_id, hf_url=hf_url)
 
-                await asyncio.sleep(300)
-                cleanup_after_upload(adapter_dir, program_id)
+                if hf_url:
+                    from api.models.database import get_engine
+                    from sqlalchemy import text as sa_text
+                    engine = get_engine()
+                    with engine.connect() as conn:
+                        conn.execute(
+                            sa_text("UPDATE programs SET hf_url = :url WHERE id = :pid"),
+                            {"url": hf_url, "pid": program_id},
+                        )
+                        conn.commit()
+                    logger.info("hf_upload_done", program_id=program_id, hf_url=hf_url)
+                    await asyncio.sleep(300)
+                    cleanup_after_upload(adapter_dir, program_id)
+                else:
+                    logger.warning("hf_upload_failed_keeping_local", program_id=program_id)
             except Exception:
                 logger.exception("background_failed", program_id=program_id)
 

{programasweights-0.2.3 → programasweights-0.2.4}/web-app/frontend/src/components/BrowserPage.tsx

@@ -239,13 +239,34 @@ const BrowserPage: React.FC = () => {
     setLoadStatus('Loading from server...');
     setLoadProgress(68);
 
-    try {
-      await loadProgramAssets(wllama, programId, true);
-    } catch (e) {
-      console.warn(`[PAW] server load failed, falling back to HF:`, e);
-      currentProgramRef.current = '';
-      await loadProgramFromHF(wllama, programId);
+    const maxWaitS = 30;
+    const intervalMs = 3000;
+    const maxAttempts = Math.ceil((maxWaitS * 1000) / intervalMs);
+
+    for (let i = 0; i < maxAttempts; i++) {
+      try {
+        const checkResp = await fetch(serverAssetUrl(programId, 'adapter.gguf'), { method: 'HEAD' });
+        if (checkResp.status === 202) {
+          console.log(`[PAW] server assets generating, retry ${i + 1}/${maxAttempts}`);
+          setLoadStatus(`Preparing program assets... (${(i + 1) * 3}s)`);
+          setLoadProgress(68 + Math.min(i, 10));
+          await new Promise(r => setTimeout(r, intervalMs));
+          continue;
+        }
+        if (checkResp.ok || checkResp.status === 302) {
+          await loadProgramAssets(wllama, programId, true);
+          return;
+        }
+        break;
+      } catch (e) {
+        console.warn(`[PAW] server check failed:`, e);
+        break;
+      }
     }
+
+    console.warn(`[PAW] server load failed or timed out, falling back to HF`);
+    currentProgramRef.current = '';
+    await loadProgramFromHF(wllama, programId);
   };
 
   const loadAndRun = async (programId: string, fromServer = false) => {