patches/0071-state-io-cosmocc.patch

From: opencoti
Subject: [PATCH 0071] cosmocc state-IO open fix (bug-269)

opencoti F5 M7 (#349, bug-269). Orthogonal to Rolling KV (0070) — captured as
its own slot. Fixes ALL llama_state_*_save/load_file in the cosmocc/llamafile
build, which were broken before this: llama.cpp/src/llama-mmap.cpp's COSMOCC
llama_file constructor routed every open() through llamafile_open_gguf(), which
pread()s the GGUF magic at offset 0 (EBADF on a write-only "wb" fd) and
zip-routes any non-GGUF read; and write_raw's fwrite(fp) ran with fp==NULL.
KV-state files are neither GGUF nor zip and are opened for write, so model
load was unaffected but state save/load never worked through the binary (the
M2 bug-222 "state round-trip" was thus never actually exercised end-to-end).

FIX (cosmocc/host-only; no CUDA, no kernel):
  * vendors/sources/llamafile/llamafile/llamafile.{c,h} (Mozilla-Ocho llamafile,
    Apache-2.0): add llamafile_open_plain() — a plain fopen-backed handle with
    no GGUF magic probe and no zip routing, for non-model files. It delegates
    to the existing static llamafile_open_file().
  * llama.cpp/src/llama-mmap.cpp: the COSMOCC llama_file ctor falls back to
    llamafile_open_plain() when llamafile_open_gguf() returns NULL (models are
    unaffected — they still open via the gguf path) and sets fp =
    llamafile_fp(lfile) so write_raw has a valid stream.

Provenance: opencoti-original. Touches Mozilla-Ocho llamafile.{c,h}
(Apache-2.0) and upstream llama.cpp llama-mmap.cpp. Applies after 0070
(independent file set — order immaterial); reverse-applies clean.
diff --git a/llama.cpp/src/llama-mmap.cpp b/llama.cpp/src/llama-mmap.cpp
--- a/llama.cpp/src/llama-mmap.cpp
+++ b/llama.cpp/src/llama-mmap.cpp
@@ -186,11 +186,25 @@ struct llama_file::impl {
 #else
     impl(const char * fname, const char * mode, [[maybe_unused]] const bool use_direct_io = false) : fname(fname) {
 #ifdef COSMOCC
-        // [llamafile] Use llamafile_open_gguf for all file opening
+        // [llamafile] Use llamafile_open_gguf for model files (raw .gguf,
+        // foo.zip@weights, /zip/ paths, and .llamafile archives via zip routing).
         lfile = llamafile_open_gguf(fname, mode);
+        // opencoti bug-269: llamafile_open_gguf is model-oriented — it pread()s the
+        // GGUF magic at offset 0 and routes non-GGUF files into a zip parser. KV
+        // state files (llama_state_*_save_file) are neither GGUF nor zip and are
+        // opened for write ("wb" → pread EBADF). Both made every state save/restore
+        // fail in the cosmocc build. When the model opener declines, fall back to a
+        // plain fopen-backed handle (model loads are unaffected — they succeed above).
+        if (lfile == NULL) {
+            lfile = llamafile_open_plain(fname, mode);
+        }
         if (lfile == NULL) {
             throw std::runtime_error(format("failed to open %s: %s", fname, strerror(errno)));
         }
+        // write_raw() writes via std::fwrite(fp); the cosmocc open path left fp NULL
+        // (read-only design). Expose the underlying FILE* so state-save writes land.
+        // Harmless for reads (read_raw_unsafe uses llamafile_read(lfile)).
+        fp = llamafile_fp(lfile);
         size = llamafile_size(lfile);
         return;
 #endif
diff --git a/llamafile/llamafile.c b/llamafile/llamafile.c
--- a/llamafile/llamafile.c
+++ b/llamafile/llamafile.c
@@ -318,6 +318,15 @@ struct llamafile *llamafile_open_gguf(const char *fname, const char *mode) {
     return llamafile_open_zip(fname, 0, mode);
 }
 
+// opencoti bug-269: plain fopen-backed handle for non-model files (KV state
+// save/load). llamafile_open_gguf() is model-oriented — it pread()s the GGUF
+// magic at offset 0 (which fails EBADF on a write-only "wb" fd) and routes any
+// non-GGUF file into a zip parser. State files are neither GGUF nor zip and are
+// opened for write, so they need a path with no magic probe and no zip routing.
+struct llamafile *llamafile_open_plain(const char *fname, const char *mode) {
+    return llamafile_open_file(fname, mode);
+}
+
 FILE *llamafile_fp(struct llamafile *file) {
     return file->fp;
 }
diff --git a/llamafile/llamafile.h b/llamafile/llamafile.h
--- a/llamafile/llamafile.h
+++ b/llamafile/llamafile.h
@@ -46,6 +46,9 @@ extern int FLAG_verbose;        // Verbose output (chatbot_main.cpp, metal.c, cu
 
 struct llamafile;
 struct llamafile *llamafile_open_gguf(const char *, const char *);  // UNUSED externally
+// opencoti bug-269: plain fopen-backed handle (no GGUF magic probe, no zip
+// routing) for non-model files such as KV state save/load.
+struct llamafile *llamafile_open_plain(const char *, const char *);
 void llamafile_close(struct llamafile *);                           // UNUSED externally
 long llamafile_read(struct llamafile *, void *, size_t);            // UNUSED externally
 long llamafile_write(struct llamafile *, const void *, size_t);     // UNUSED externally