programasweights 0.2.4__tar.gz → 0.2.5__tar.gz

{programasweights-0.2.4 → programasweights-0.2.5}/AGENTS.md

@@ -81,6 +81,21 @@ Output: delete
 - Each function is stateless: one input, one output. No conversation history.
 - Write a few test inputs with expected outputs, then try different spec phrasings and pick the one that passes the most.
 
+## Chaining Functions
+
+Multiple PAW functions can be composed for multi-step tasks:
+
+```python
+classifier = paw.compile_and_load("Classify the bug type. Return ONLY one of: off-by-one, type-error, other")
+fixer = paw.compile_and_load("Fix the bug described in the first line. Return only the corrected code.")
+
+label = classifier(code_snippet)
+if label != "other":
+    fix = fixer(f"{label}: {code_snippet}")
+```
+
+Each function is independent -- chain them with regular Python logic.
+
 ## Browser / JavaScript SDK
 
 Programs compiled with `paw-4b-gpt2` run in the browser via WebAssembly.
@@ -143,7 +158,7 @@ fn = paw.function(program)              # accepts Program object, hash ID, or sl
 fn = paw.function("a6b454023d41ac9ca845")
 fn = paw.function("da03/my-classifier")
 
-result: str = fn(input_text: str, max_tokens=512, temperature=0.0)
+result: str = fn(input_text: str, max_tokens=None, temperature=0.0)
 
 fn = paw.compile_and_load(spec, compiler="paw-4b-qwen3-0.6b")
 
@@ -156,7 +171,7 @@ paw.login()
 
 | Error | Cause | Fix |
 |-------|-------|-----|
-| `httpx.HTTPStatusError: 404` on download | Program still uploading to CDN | SDK retries automatically. If persistent, recompile. |
+| `RuntimeError: assets not ready` on download | Program still generating after compile | SDK polls automatically for up to 30s. If persistent, recompile. |
 | `httpx.HTTPStatusError: 422` on compile | Spec too short (<10 chars) | Adjust spec length. |
 | `httpx.HTTPStatusError: 429` | Rate limit exceeded | Wait, or sign in for higher limits. |
 
@@ -168,6 +183,11 @@ paw.login()
 - **Cache**: `~/.cache/programasweights/`. Override with `PAW_CACHE_DIR`.
 - **Offline** after first download.
 
+## Limits
+
+- Spec + input + output share a ~2048 token context window, and inputs that exceed the context window will error out (not silently truncated).
+- Setting `max_tokens` high is safe -- generation stops at EOS or when the window is full.
+
 ## Browse Programs
 
 https://programasweights.com/hub

{programasweights-0.2.4 → programasweights-0.2.5}/CHANGELOG.md

@@ -1,5 +1,16 @@
 # Changelog
 
+## 0.2.4 (2026-04-01)
+
+- Download reliability: asset endpoints return 202 Retry-After when program is still generating, eliminating 404 race conditions
+- Guard local cleanup on HF upload success: files persist locally if upload fails
+- Stderr suppression now covers LoRA adapter loading (fixes CPU_REPACK warnings on 0.2.3)
+- Browser: fix LoRA switching bug (free old adapter + clear KV before loading new program)
+
+## 0.2.3 (2026-04-01)
+
+- Python 3.9 compatibility fix (`from __future__ import annotations`)
+
 ## 0.2.2 (2026-03-19)
 
 - Add `paw.compile_and_load()` convenience method (compile + load in one call)

{programasweights-0.2.4 → programasweights-0.2.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: programasweights
-Version: 0.2.4
+Version: 0.2.5
 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-0.2.4 → programasweights-0.2.5}/docs/api-reference/python-sdk.md

@@ -32,15 +32,17 @@ Loads a compiled program and returns a callable. Downloads the program and base
 The returned callable:
 
 ```python
-output: str = fn(input_text, max_tokens=512, temperature=0.0)
+output: str = fn(input_text, max_tokens=None, temperature=0.0)
 ```
 
 | Parameter | Description |
 |-----------|-------------|
 | `input_text` | Input string for the program. |
-| `max_tokens` | Maximum tokens to generate (default `512`). |
+| `max_tokens` | Maximum tokens to generate. `None` (default) = use all remaining context window. |
 | `temperature` | Sampling temperature (default `0.0`). |
 
+**Context limits:** Spec + input + output share a ~2048 token window. If input + output together exceed the window, generation will error. For short inputs, high `max_tokens` is safe (stops at EOS). For long inputs, set `max_tokens` conservatively.
+
 ## `paw.compile`
 
 ```python

{programasweights-0.2.4 → programasweights-0.2.5}/docs/api-reference/rest-api.md

@@ -34,7 +34,11 @@ Compile a specification.
 | `name` | string | No | Display title. Auto-generated if omitted. |
 | `tags` | string[] | No | Tags for discovery. |
 
-**Response (JSON):** includes `job_id`, `status`, `program_id`, `slug` (if created), `pseudo_program`, and `timings`.
+**Response:**
+- **202 Accepted** on success — JSON with `job_id`, `status`, `program_id`, `slug` (if created), `pseudo_program`, and `timings`
+- **400** — unknown compiler
+- **422** — spec too short, too long, or token limit exceeded
+- **500** — compilation failed (server error)
 
 ### `POST /infer`
 
@@ -88,7 +92,11 @@ Owner-only fields: `public`, `name`, `tags`. Any authenticated user can set thei
 
 ### `GET /programs/{id_or_slug}/download`
 
-Redirects to the Hugging Face CDN for the `.paw` artifact. Private programs return 404 to non-owners.
+Downloads the `.paw` artifact. Returns one of:
+- **302** redirect to HuggingFace CDN (program already uploaded)
+- **200** file from server (freshly compiled, not yet on HF)
+- **202 Accepted** with `Retry-After` header (program assets still generating, retry after the indicated seconds)
+- **404** if program not found or private and not owned by the requester
 
 ### `GET /programs/resolve/{slug}`
 

{programasweights-0.2.4 → programasweights-0.2.5}/programasweights/__init__.py

@@ -23,7 +23,7 @@ API reference:
 """
 from __future__ import annotations
 
-__version__ = "0.2.4"
+__version__ = "0.2.5"
 
 from .config import get_api_url, get_api_key, set_api_key
 

{programasweights-0.2.4 → programasweights-0.2.5}/programasweights/runtime_llamacpp.py

@@ -37,6 +37,7 @@ class PawFunction:
         program_dir = Path(program_dir)
         self._program_dir = program_dir
         self._verbose = verbose
+        self._n_ctx = n_ctx
 
         meta_path = program_dir / "meta.json"
         if meta_path.exists():
@@ -151,20 +152,19 @@ class PawFunction:
     def __call__(
         self,
         input_text: str,
-        max_tokens: int = 512,
+        max_tokens: int | None = None,
         temperature: float = 0.0,
     ) -> str:
         """Run the program on an input.
 
         Args:
             input_text: The input to process.
-            max_tokens: Maximum output tokens.
+            max_tokens: Maximum output tokens. None = use all remaining context.
             temperature: Sampling temperature (0 = greedy).
 
         Returns:
             The program's output as a string.
         """
-        # Reset to prefix state: clear everything after the prefix
         self._llm.n_tokens = self._n_prefix
 
         input_with_suffix = input_text + self._suffix_text
@@ -174,10 +174,21 @@ class PawFunction:
             special=self._use_special,
         )
 
+        tokens_used = self._n_prefix + len(input_tokens)
+        remaining = self._n_ctx - tokens_used
+        if remaining <= 0:
+            raise ValueError(
+                f"Input too long: {tokens_used} tokens used (prefix={self._n_prefix}, "
+                f"input={len(input_tokens)}), context window={self._n_ctx}. "
+                f"Shorten your input."
+            )
+
+        gen_limit = remaining if max_tokens is None else min(max_tokens, remaining)
+
         self._llm.eval(input_tokens)
 
         output_tokens = []
-        for _ in range(max_tokens):
+        for _ in range(gen_limit):
             token = self._llm.sample(
                 temp=temperature if temperature > 0 else 0,
             )

{programasweights-0.2.4 → programasweights-0.2.5}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "programasweights"
-version = "0.2.4"
+version = "0.2.5"
 description = "Compile natural language specifications into neural programs that run locally via llama.cpp."
 readme = "PYPI_README.md"
 requires-python = ">=3.9"

{programasweights-0.2.4 → programasweights-0.2.5}/server/api/main.py

@@ -57,6 +57,9 @@ class _FallbackLimiter:
         return True
 
 
+_API_VERSION = "0.4.0"
+
+
 def create_app() -> FastAPI:
     settings = get_settings()
     configure_logging(
@@ -64,10 +67,13 @@ def create_app() -> FastAPI:
         json_format=(settings.LOG_FORMAT == "json"),
     )
 
+    if settings.JWT_SECRET == "dev-secret-change-in-production":
+        raise RuntimeError("JWT_SECRET must be set in .env -- refusing to start with the default value")
+
     app = FastAPI(
         title="Programs as Weights API",
         description="Compile natural language specs into neural functions",
-        version="0.4.0",
+        version=_API_VERSION,
         docs_url="/api/docs",
         openapi_url="/api/openapi.json",
     )

{programasweights-0.2.4 → programasweights-0.2.5}/server/api/routes/auth.py

@@ -21,10 +21,20 @@ from api.models.orm import User
 logger = structlog.get_logger()
 router = APIRouter()
 
-# In-memory session store (replace with Redis/DB for production)
+# In-memory session store (single-process; cleaned periodically)
 _sessions: dict[str, dict] = {}
 _github_states: dict[str, float] = {}
 
+_SESSION_MAX_AGE = 30 * 24 * 3600  # 30 days, matches cookie max_age
+
+
+def _cleanup_expired_sessions():
+    cutoff = time.time() - _SESSION_MAX_AGE
+    expired = [k for k, v in _sessions.items() if v.get("created_at", 0) < cutoff]
+    for k in expired:
+        del _sessions[k]
+
+
 GITHUB_AUTHORIZE_URL = "https://github.com/login/oauth/authorize"
 GITHUB_TOKEN_URL = "https://github.com/login/oauth/access_token"
 GITHUB_USER_URL = "https://api.github.com/user"
@@ -44,6 +54,8 @@ async def github_login(request: Request):
     for k in [k for k, v in _github_states.items() if v < cutoff]:
         del _github_states[k]
 
+    _cleanup_expired_sessions()
+
     params = (
         f"?client_id={settings.GITHUB_CLIENT_ID}"
         f"&redirect_uri=https://programasweights.com/api/v1/auth/github/callback"

{programasweights-0.2.4 → programasweights-0.2.5}/server/api/routes/compile.py

@@ -2,6 +2,7 @@
 Compile endpoint: submit specs for compilation into neural programs.
 """
 
+import time
 import uuid
 
 import httpx
@@ -19,8 +20,18 @@ logger = structlog.get_logger()
 
 router = APIRouter()
 
-# In-memory job store (will be replaced with PostgreSQL + Celery)
+# In-memory job store (single-process; evicted after 1 hour)
 _jobs: dict[str, dict] = {}
+_JOBS_MAX_AGE = 3600
+
+
+def _evict_old_jobs():
+    import time as _time
+    cutoff = _time.time() - _JOBS_MAX_AGE
+    expired = [k for k, v in _jobs.items() if v.get("created_at", 0) < cutoff]
+    for k in expired:
+        del _jobs[k]
+
 
 # Compiler registry loaded from JSON file
 import json as _json
@@ -87,6 +98,8 @@ async def submit_compile(
             },
         )
 
+    _evict_old_jobs()
+
     job_id = str(uuid.uuid4())[:12]
     _jobs[job_id] = {
         "status": "queued",
@@ -94,6 +107,7 @@ async def submit_compile(
         "compiler_snapshot": snapshot,
         "program_id": None,
         "error": None,
+        "created_at": time.time(),
     }
 
     import asyncio
@@ -244,12 +258,11 @@ async def submit_compile(
         _jobs[job_id]["error"] = str(e)
         logger.exception("compile_failed", spec_len=len(req.spec), error=str(e))
 
-        return CompileResponse(
-            job_id=job_id,
-            status="failed",
-            compiler_snapshot=snapshot,
-            error=str(e),
-        )
+        raise HTTPException(status_code=500, detail={
+            "error": "compile_failed",
+            "message": "Compilation failed. Please try again.",
+            "request_id": getattr(request.state, "request_id", "unknown"),
+        })
 
 
 @router.get("/compile/{job_id}", response_model=CompileStatusResponse)

{programasweights-0.2.4 → programasweights-0.2.5}/server/api/routes/health.py

@@ -8,6 +8,8 @@ from fastapi import APIRouter, Request
 
 from api.models.schemas import HealthResponse
 
+_API_VERSION = "0.4.0"
+
 router = APIRouter()
 
 _start_time = time.time()
@@ -21,7 +23,7 @@ async def health_check(request: Request):
 
     return HealthResponse(
         status="healthy" if not warnings else "degraded",
-        version="0.2.0",
+        version=_API_VERSION,
         gpu_services={},
         queue_depth=0,
         uptime_s=time.time() - _start_time,

{programasweights-0.2.4 → programasweights-0.2.5}/server/api/routes/infer.py

@@ -107,9 +107,9 @@ async def run_inference(
     except HTTPException:
         raise
     except Exception as e:
-        logger.exception("infer_proxy_failed", program_id=canonical_id)
+        logger.exception("infer_proxy_failed", program_id=canonical_id, error=str(e))
         raise HTTPException(status_code=502, detail={
             "error": "inference_failed",
-            "message": str(e)[:200],
+            "message": "Inference failed. Please try again.",
             "request_id": request_id,
         })

{programasweights-0.2.4 → programasweights-0.2.5}/server/api/routes/programs.py

@@ -125,6 +125,8 @@ async def list_programs(
 ):
     from sqlalchemy import text as sa_text
 
+    per_page = min(per_page, 100)
+
     if mine and user:
         aliased_ids = select(Alias.program_id).where(Alias.owner_id == user.id).scalar_subquery()
         query = select(Program).where(
@@ -201,7 +203,7 @@ async def list_programs(
                 use_fts = True
             else:
                 alias_match = select(Alias.program_id).where(
-                    Alias.slug.ilike(f"%{search_term}%")
+                    Alias.slug_name.ilike(f"%{search_term}%")
                 ).scalar_subquery()
                 conditions = [
                     Program.spec.ilike(f"%{search_term}%"),

{programasweights-0.2.4 → programasweights-0.2.5}/web-app/frontend/src/App.tsx

@@ -1,4 +1,4 @@
-import { BrowserRouter as Router, Routes, Route, Navigate, useLocation } from 'react-router-dom';
+import { BrowserRouter as Router, Routes, Route, Navigate, useLocation, Link } from 'react-router-dom';
 import { Component, useEffect } from 'react';
 import type { ReactNode } from 'react';
 import { Toaster } from 'react-hot-toast';
@@ -55,6 +55,18 @@ class ErrorBoundary extends Component<{ children: ReactNode }, { hasError: boole
   }
 }
 
+function NotFoundPage() {
+  return (
+    <div className="min-h-[60vh] flex items-center justify-center">
+      <div className="text-center">
+        <h1 className="text-6xl font-bold text-gray-300 mb-4">404</h1>
+        <p className="text-xl text-gray-600 mb-6">Page not found</p>
+        <Link to="/" className="px-5 py-2.5 bg-gray-900 text-white rounded-lg hover:bg-gray-800 transition-colors text-sm font-medium">Back to home</Link>
+      </div>
+    </div>
+  );
+}
+
 function App() {
   return (
     <ErrorBoundary>
@@ -96,6 +108,8 @@ function App() {
             <Route path="/leaderboard" element={<Navigate to="/hub?sort=popular" replace />} />
             <Route path="/program/:id" element={<Navigate to="/hub" replace />} />
             <Route path="/publish" element={<Navigate to="/hub/upload" replace />} />
+
+            <Route path="*" element={<NotFoundPage />} />
           </Routes>
         </main>
         <Footer />

programasweights-0.2.5/web-app/frontend/src/components/AgentsPage.tsx

@@ -0,0 +1,92 @@
+import { useState } from 'react';
+import { Helmet } from 'react-helmet-async';
+import { Copy, Check, MessageSquare, FileText } from 'lucide-react';
+import toast from 'react-hot-toast';
+import AGENTS_MD from '../../../../AGENTS.md?raw';
+
+const CHAT_PROMPT = `I want to use ProgramAsWeights (PAW) to create fuzzy text functions (search, classification, format repair, etc.) that run locally. Read the instructions at https://programasweights.com/agents and help me integrate it into my project. [Describe your use case briefly.]`;
+
+const CursorRulePage: React.FC = () => {
+  const [copiedChat, setCopiedChat] = useState(false);
+  const [copiedFile, setCopiedFile] = useState(false);
+
+  return (
+    <div className="max-w-3xl mx-auto space-y-6">
+      <Helmet><title>AI Agents — PAW</title></Helmet>
+      <div>
+        <h1 className="text-2xl font-bold text-gray-900">Use PAW with AI Agents</h1>
+        <p className="text-gray-600 mt-2">
+          Let your AI coding assistant (Cursor, Claude, Codex, etc.) use PAW to create fuzzy text functions.
+        </p>
+      </div>
+
+      <div className="bg-white rounded-xl border-2 border-blue-200 shadow-sm p-6 space-y-3">
+        <div className="flex items-center gap-2">
+          <MessageSquare className="w-5 h-5 text-blue-600" />
+          <h2 className="text-lg font-semibold text-gray-900">Paste into your agent's chat</h2>
+          <span className="px-2 py-0.5 bg-blue-100 text-blue-700 text-[10px] rounded-full font-semibold uppercase">Recommended</span>
+        </div>
+        <p className="text-sm text-gray-500">
+          Copy this prompt and paste it into Cursor, Claude, Codex, or any AI assistant. It will read the link and know how to use PAW.
+        </p>
+        <div className="bg-gray-50 rounded-lg p-4 text-sm text-gray-700 leading-relaxed">
+          {CHAT_PROMPT}
+        </div>
+        <button
+          onClick={() => {
+            navigator.clipboard.writeText(CHAT_PROMPT).catch(() => {});
+            setCopiedChat(true);
+            toast.success('Copied! Paste into your AI agent\'s chat.');
+            setTimeout(() => setCopiedChat(false), 3000);
+          }}
+          className="flex items-center gap-2 px-5 py-2.5 bg-blue-600 text-white rounded-lg font-medium text-sm hover:bg-blue-700 transition-colors"
+        >
+          {copiedChat ? <Check className="w-4 h-4" /> : <Copy className="w-4 h-4" />}
+          {copiedChat ? 'Copied!' : 'Copy prompt'}
+        </button>
+      </div>
+
+      <div className="bg-white rounded-xl border border-gray-200 shadow-sm p-6 space-y-3">
+        <div className="flex items-center gap-2">
+          <FileText className="w-5 h-5 text-gray-500" />
+          <h2 className="text-lg font-semibold text-gray-900">Or save as a project file</h2>
+        </div>
+        <p className="text-sm text-gray-500">
+          For persistent access, save as <code className="bg-gray-100 px-1.5 py-0.5 rounded text-xs">AGENTS.md</code> in your project root.
+          AI agents will automatically read it.
+        </p>
+        <button
+          onClick={() => {
+            navigator.clipboard.writeText(AGENTS_MD).catch(() => {});
+            setCopiedFile(true);
+            toast.success('Copied! Save as AGENTS.md in your project root.');
+            setTimeout(() => setCopiedFile(false), 3000);
+          }}
+          className="flex items-center gap-2 px-5 py-2.5 bg-gray-900 text-white rounded-lg font-medium text-sm hover:bg-gray-800 transition-colors"
+        >
+          {copiedFile ? <Check className="w-4 h-4" /> : <Copy className="w-4 h-4" />}
+          {copiedFile ? 'Copied!' : 'Copy AGENTS.md'}
+        </button>
+      </div>
+
+      <div className="bg-blue-50 border border-blue-200 rounded-xl p-4">
+        <h3 className="text-sm font-semibold text-blue-900 mb-2">Which SDK?</h3>
+        <div className="text-sm text-blue-700 space-y-1">
+          <p><strong>Python SDK</strong> — server-side backends, pipelines. Standard interpreter (Qwen3 0.6B, best accuracy).</p>
+          <p><strong>Browser SDK</strong> — client-side web apps, data stays on user's device. Compact interpreter (GPT-2 124M).</p>
+        </div>
+      </div>
+
+      <details className="bg-white rounded-xl border border-gray-200 shadow-sm overflow-hidden">
+        <summary className="px-6 py-4 cursor-pointer text-sm font-medium text-gray-700 hover:bg-gray-50">
+          View full AGENTS.md content
+        </summary>
+        <pre className="px-6 pb-6 text-xs text-gray-600 overflow-x-auto whitespace-pre-wrap leading-relaxed max-h-[400px] overflow-y-auto border-t border-gray-100 pt-4">
+          {AGENTS_MD}
+        </pre>
+      </details>
+    </div>
+  );
+};
+
+export default CursorRulePage;