Merge remote-tracking branch 'origin/dev' into pr259

# Conflicts:
#	README.md

c/tests/test_compat_direct.c

@@ -51,6 +51,23 @@ int main(void){
     if(compat_open_direct("no_such_file.tmp")>=0) return fail("open missing file must fail");
     if(compat_fsize(-1)>=0) return fail("compat_fsize on bad fd must be negative");
 
+    /* compat_fadvise: WILLNEED warms the page cache (background read into throwaway
+     * buffer), DONTNEED is a documented no-op. After a WILLNEED the buffered fd's
+     * subsequent pread must still return the exact bytes — the cache-warmer must not
+     * corrupt data. Bad fd / non-WILLNEED advice must be safe no-ops (return 0). */
+    int wfd = open(TMPF, COMPAT_O_RDONLY);
+    if(wfd<0) return fail("open buffered for fadvise");
+    if(posix_fadvise(wfd, 0, (off_t)FSZ, POSIX_FADV_WILLNEED)!=0) return fail("WILLNEED returned nonzero");
+    if(posix_fadvise(wfd, 0, (off_t)FSZ, POSIX_FADV_DONTNEED)!=0) return fail("DONTNEED should be a safe no-op (return 0)");
+    if(posix_fadvise(-1, 0, (off_t)FSZ, POSIX_FADV_WILLNEED)!=0) return fail("WILLNEED on bad fd should no-op (return 0)");
+    if(posix_fadvise(wfd, 0, 0, POSIX_FADV_WILLNEED)!=0) return fail("WILLNEED with len<=0 should no-op");
+    /* verify data integrity through the buffered fd after the cache-warmer ran */
+    uint8_t *verify=malloc(FSZ);
+    if(pread(wfd, verify, FSZ, 0)!=(ssize_t)FSZ) return fail("fadvise: pread size");
+    if(memcmp(verify, pat, FSZ)!=0) return fail("fadvise: data corrupted by cache-warmer");
+    free(verify);
+    close(wfd);
+
     close(dfd);
     compat_aligned_free(buf); free(pat); remove(TMPF);
     puts("compat direct tests: ok");

c/tests/test_openai_server.py

@@ -72,8 +72,13 @@ class TemplateTest(unittest.TestCase):
     def test_validates_generation_limits(self):
         self.assertEqual(generation_options({"max_tokens": 4, "temperature": 0, "top_p": 1}, 8),
                          (4, 0.0, 1.0))
+        # max_tokens above the server cap is clamped, not rejected (#260): OpenAI
+        # clients default to large values; erroring breaks them.
+        self.assertEqual(generation_options({"max_tokens": 9, "temperature": 0, "top_p": 1}, 8),
+                         (8, 0.0, 1.0))
+        # non-positive / non-int max_tokens is still a hard error
         with self.assertRaises(APIError):
-            generation_options({"max_tokens": 9}, 8)
+            generation_options({"max_tokens": 0}, 8)
         with self.assertRaises(APIError):
             generation_options({"temperature": math.nan}, 8)
         with self.assertRaises(APIError):