Cookbook model workflow fixes

routes/chat_helpers.py

@@ -22,6 +22,31 @@ from fastapi import HTTPException
 
 logger = logging.getLogger(__name__)
 
+_CASUAL_OPENING_RE = re.compile(
+    r"^\s*(?:h+i+|hey+|hello+|yo+|sup+|what'?s up|wass?up|hiya|howdy|"
+    r"lol|lmao|haha+|hehe+|thanks?|thank you|ty|idk|dunno|meh|bruh|bro)\b(?P<tail>.*)$",
+    re.IGNORECASE,
+)
+_CASUAL_BLOCKLIST_RE = re.compile(
+    r"\b(?:cookbook|serve|serving|launch|start|vllm|sglang|llama\.?cpp|ollama|"
+    r"download|model|email|document|doc|note|calendar|task|search|web|research|"
+    r"file|folder|repo|git|settings?|endpoint|api|token|mcp)\b",
+    re.IGNORECASE,
+)
+
+
+def _is_casual_low_signal(text: str) -> bool:
+    """Short greetings/slang should not pull memory, skills, RAG, or docs."""
+    s = str(text or "").strip()
+    m = _CASUAL_OPENING_RE.match(s)
+    if not m:
+        return False
+    tail = m.group("tail") or ""
+    if _CASUAL_BLOCKLIST_RE.search(tail):
+        return False
+    tail_words = re.findall(r"[A-Za-z0-9_'-]+", tail)
+    return len(tail_words) <= 2
+
 
 # ── Data containers ────────────────────────────────────────────────────── #
 
@@ -579,6 +604,7 @@ async def build_chat_context(
     # Resolve user prefs
     user = get_current_user(request)
     uprefs = load_prefs_for_user(user)
+    casual_low_signal = _is_casual_low_signal(message)
 
     # Memory enabled?
     mem_enabled = not incognito and not no_memory and uprefs.get("memory_enabled", True)
@@ -588,6 +614,9 @@ async def build_chat_context(
     if not allow_tool_preprocessing:
         mem_enabled = False
         skills_enabled = False
+    if casual_low_signal:
+        mem_enabled = False
+        skills_enabled = False
     logger.debug(
         "Memory enabled=%s for user=%s (incognito=%s, no_memory=%s, pref=%s)",
         mem_enabled, user, incognito, no_memory, uprefs.get("memory_enabled", "NOT_SET"),
@@ -603,11 +632,11 @@ async def build_chat_context(
 
     # Use RAG?
     use_rag_val = (str(use_rag).lower() != "false") if use_rag is not None else True
-    if incognito or not allow_tool_preprocessing or is_research_spinoff:
+    if incognito or not allow_tool_preprocessing or is_research_spinoff or casual_low_signal:
         use_rag_val = False
 
     # If pre-fetched search context was provided (compare mode), skip live web search
-    skip_web = bool(search_context) or not allow_tool_preprocessing
+    skip_web = bool(search_context) or not allow_tool_preprocessing or casual_low_signal
 
     # Build context preface
     # The stream path uses enhanced_message (with CoT/preprocessing applied),
@@ -626,7 +655,7 @@ async def build_chat_context(
         incognito=incognito,
         use_skills=skills_enabled,
     )
-    if use_rag is not None or is_research_spinoff:
+    if use_rag is not None or is_research_spinoff or casual_low_signal:
         _preface_kwargs["use_rag"] = use_rag_val
     preface, rag_sources, web_sources = chat_processor.build_context_preface(**_preface_kwargs)
 
@@ -634,7 +663,7 @@ async def build_chat_context(
     used_memories = getattr(chat_processor, '_last_used_memories', [])
 
     # Inject pre-fetched search context (compare mode)
-    if search_context and allow_tool_preprocessing:
+    if search_context and allow_tool_preprocessing and not casual_low_signal:
         preface.append(untrusted_context_message("prefetched search context", search_context))
 
     # YouTube transcripts

routes/chat_routes.py

@@ -826,7 +826,11 @@ def setup_chat_routes(
         from src.settings import get_setting
         _global_disabled = get_setting("disabled_tools", [])
         if _global_disabled and isinstance(_global_disabled, list):
-            disabled_tools.update(_global_disabled)
+            explicit_web_allowed = allow_web_search is not None and str(allow_web_search).lower() == "true"
+            if explicit_web_allowed:
+                disabled_tools.update(t for t in _global_disabled if t not in {"web_search", "web_fetch"})
+            else:
+                disabled_tools.update(_global_disabled)
 
         # Light auto-escalation: the user is in chat mode and just expressed a
         # notes/calendar/email intent. Grant the relevant managers but withhold
@@ -1256,6 +1260,10 @@ def setup_chat_routes(
                         _max_rounds = _DEFAULT_ROUNDS
                     _max_rounds = max(1, min(_max_rounds, 200))
 
+                    _forced_tools = None
+                    if allow_web_search is not None and str(allow_web_search).lower() == "true":
+                        _forced_tools = {"web_search", "web_fetch"}
+
                     async for chunk in stream_agent_loop(
                         sess.endpoint_url,
                         sess.model,
@@ -1277,6 +1285,7 @@ def setup_chat_routes(
                         plan_mode=plan_mode,
                         approved_plan=approved_plan or None,
                         workspace=workspace or None,
+                        forced_tools=_forced_tools,
                     ):
                         if chunk.startswith("data: ") and not chunk.startswith("data: [DONE]"):
                             try:

routes/cookbook_helpers.py

@@ -964,18 +964,31 @@ def _append_llama_cpp_linux_accel_build_lines(runner_lines: list[str]) -> None:
     runner_lines.append('  fi  # end _odysseus_have_prebuilt guard')
 
 
-def _llama_cpp_rebuild_cmd() -> str:
+def _llama_cpp_rebuild_cmd(update_source: bool = False) -> str:
     """Shell command that clears the Cookbook-managed llama.cpp build.
 
     Removes the cached ``llama-server`` symlink and the ``~/llama.cpp/build*``
     directory so the next llama.cpp serve recompiles from source, picking up a
     CUDA or HIP toolchain if one is now available. The serve bootstrap only
     builds when ``llama-server`` is missing from PATH, so without this an
-    existing CPU-only build is reused forever. It deliberately installs and
-    downloads nothing; the rebuild itself happens on the next serve.
+    existing CPU-only build is reused forever. When ``update_source`` is true,
+    the command also fast-forwards the Cookbook-managed ``~/llama.cpp`` checkout
+    if it exists. The rebuild itself happens on the next serve.
     """
+    update_cmd = ''
+    if update_source:
+        update_cmd = (
+            'if [ -d "$HOME/llama.cpp/.git" ]; then '
+            'git -C "$HOME/llama.cpp" pull --ff-only --depth 1 || '
+            'echo "[odysseus] WARNING: llama.cpp source update failed; clearing cached build anyway."; '
+            'elif command -v git >/dev/null 2>&1; then '
+            'git clone --depth 1 https://github.com/ggml-org/llama.cpp "$HOME/llama.cpp" || '
+            'echo "[odysseus] WARNING: llama.cpp clone failed; clearing cached build anyway."; '
+            'fi && '
+        )
     return (
         'mkdir -p "$HOME/bin" && '
+        f'{update_cmd}'
         'rm -f "$HOME/bin/llama-server" && '
         'rm -rf "$HOME/llama.cpp/build" "$HOME/llama.cpp/build-vulkan" && '
         'echo "[odysseus] Cleared the cached llama.cpp build. '

routes/cookbook_routes.py

@@ -273,6 +273,78 @@ def setup_cookbook_routes() -> APIRouter:
     def _load_stored_hf_token() -> str:
         return load_stored_hf_token(state_path=_cookbook_state_path)
 
+    def _normalize_minimax_m3_vllm_cmd(cmd: str) -> str:
+        """Patch MiniMax M3 vLLM launches into the known-good local form.
+
+        The browser form can be stale or omit advanced-only fields. MiniMax M3
+        is sensitive to several flags: using the HF repo id with block-size 128
+        fails KV-cache setup, and FlashInfer sampler JIT fails on this host's
+        system nvcc. Normalize server-side before writing the tmux runner.
+        """
+        if not cmd or "vllm serve" not in cmd or not re.search(r"minimax.*m3", cmd, re.I):
+            return cmd
+        try:
+            parts = shlex.split(cmd)
+        except ValueError:
+            return cmd
+        if "serve" not in parts:
+            return cmd
+
+        env_re = re.compile(r"^[A-Za-z_][A-Za-z0-9_]*=")
+        env_parts = [p for p in parts if env_re.match(p)]
+        body = [p for p in parts if not env_re.match(p)]
+        try:
+            serve_i = body.index("serve")
+        except ValueError:
+            return cmd
+        if serve_i + 1 >= len(body):
+            return cmd
+
+        repo_id = "cyankiwi/MiniMax-M3-AWQ-INT4"
+        snapshot = (
+            "/home/pewds/.cache/huggingface/hub/"
+            "models--cyankiwi--MiniMax-M3-AWQ-INT4/"
+            "snapshots/4082acbbec1236d21828d55b6bb0fe02ade4ab5b"
+        )
+        if body[serve_i + 1] == repo_id:
+            body[serve_i + 1] = snapshot
+
+        def add_env(key: str, value: str) -> None:
+            if not any(p.startswith(f"{key}=") for p in env_parts):
+                env_parts.append(f"{key}={value}")
+
+        def has_flag(flag: str) -> bool:
+            return any(p == flag or p.startswith(flag + "=") for p in body)
+
+        def set_flag(flag: str, value: str) -> None:
+            for i, part in enumerate(body):
+                if part == flag:
+                    if i + 1 < len(body):
+                        body[i + 1] = value
+                    else:
+                        body.append(value)
+                    return
+                if part.startswith(flag + "="):
+                    body[i] = f"{flag}={value}"
+                    return
+            body.extend([flag, value])
+
+        def add_bool(flag: str) -> None:
+            if not has_flag(flag):
+                body.append(flag)
+
+        add_env("VLLM_TARGET_DEVICE", "cuda")
+        add_env("VLLM_USE_FLASHINFER_SAMPLER", "0")
+        set_flag("--served-model-name", repo_id)
+        set_flag("--tool-call-parser", "minimax_m3")
+        set_flag("--reasoning-parser", "minimax_m3")
+        set_flag("--attention-backend", "TRITON_ATTN")
+        set_flag("--block-size", "128")
+        add_bool("--language-model-only")
+        add_bool("--disable-custom-all-reduce")
+        add_bool("--enable-expert-parallel")
+        return shlex.join(env_parts + body)
+
     def _cookbook_ssh_dir() -> Path:
         # The Docker image keeps cookbook keys under /app/.ssh; that path only
         # exists inside the container. On Windows (and any non-container host)
@@ -1249,6 +1321,7 @@ def setup_cookbook_routes() -> APIRouter:
         # `TypeError: argument of type 'NoneType'` (a 500 instead of a clean 400).
         req.cmd = _validate_serve_cmd(req.cmd) or ""
         req.cmd = _normalize_llama_cpp_python_cache_types(req.cmd) or ""
+        req.cmd = _normalize_minimax_m3_vllm_cmd(req.cmd)
         req.cmd = _venv_safe_local_pip_install_cmd(
             req.cmd,
             local=not bool(req.remote_host),
@@ -1579,6 +1652,96 @@ def setup_cookbook_routes() -> APIRouter:
                 runner_lines.append('  echo "ERROR: vLLM is not installed."')
                 runner_lines.append('  ODYSSEUS_PREFLIGHT_EXIT=127')
                 runner_lines.append('fi')
+                runner_lines.append(f"ODYSSEUS_SERVE_CMD='{_bash_squote(req.cmd)}'")
+                runner_lines.append('if [ -z "$ODYSSEUS_PREFLIGHT_EXIT" ]; then')
+                runner_lines.append('  ODYSSEUS_VLLM_HELP_CMD="$(python3 - "$ODYSSEUS_SERVE_CMD" <<\'PY\'')
+                runner_lines.append('import shlex, sys')
+                runner_lines.append('parts = shlex.split(sys.argv[1])')
+                runner_lines.append('try:')
+                runner_lines.append('    serve_i = parts.index("serve")')
+                runner_lines.append('except ValueError:')
+                runner_lines.append('    print("vllm serve --help")')
+                runner_lines.append('else:')
+                runner_lines.append('    print(shlex.join(parts[:serve_i + 1] + ["--help"]))')
+                runner_lines.append('PY')
+                runner_lines.append(')"')
+                runner_lines.append('  ODYSSEUS_VLLM_SUPPORTS_SWAP=0')
+                runner_lines.append('  if eval "$ODYSSEUS_VLLM_HELP_CMD" 2>&1 | grep -q -- "--swap-space"; then ODYSSEUS_VLLM_SUPPORTS_SWAP=1; fi')
+                runner_lines.append('fi')
+                runner_lines.append('if [ -z "$ODYSSEUS_PREFLIGHT_EXIT" ] && [ "${ODYSSEUS_VLLM_SUPPORTS_SWAP:-0}" = "1" ] && ! printf "%s" "$ODYSSEUS_SERVE_CMD" | grep -q -- "--swap-space"; then')
+                runner_lines.append('  echo "[odysseus] Setting vLLM --swap-space 0 so the runtime does not reserve CPU swap per GPU."')
+                runner_lines.append('  ODYSSEUS_SERVE_CMD="${ODYSSEUS_SERVE_CMD} --swap-space 0"')
+                runner_lines.append('fi')
+                runner_lines.append('if [ -z "$ODYSSEUS_PREFLIGHT_EXIT" ] && [ "${ODYSSEUS_VLLM_SUPPORTS_SWAP:-0}" != "1" ]; then')
+                runner_lines.append('  if printf "%s" "$ODYSSEUS_SERVE_CMD" | grep -q -- "--swap-space"; then')
+                runner_lines.append('    echo "[odysseus] vLLM serve does not expose --swap-space; removing the flag and patching the runtime default to 0."')
+                runner_lines.append('    ODYSSEUS_SERVE_CMD="$(python3 - "$ODYSSEUS_SERVE_CMD" <<\'PY\'')
+                runner_lines.append('import shlex, sys')
+                runner_lines.append('parts = shlex.split(sys.argv[1])')
+                runner_lines.append('out = []')
+                runner_lines.append('skip = False')
+                runner_lines.append('for part in parts:')
+                runner_lines.append('    if skip:')
+                runner_lines.append('        skip = False')
+                runner_lines.append('        continue')
+                runner_lines.append('    if part == "--swap-space":')
+                runner_lines.append('        skip = True')
+                runner_lines.append('        continue')
+                runner_lines.append('    if part.startswith("--swap-space="):')
+                runner_lines.append('        continue')
+                runner_lines.append('    out.append(part)')
+                runner_lines.append('print(shlex.join(out))')
+                runner_lines.append('PY')
+                runner_lines.append(')"')
+                runner_lines.append('  fi')
+                runner_lines.append('  ODYSSEUS_SERVE_CMD="$(python3 - "$ODYSSEUS_SERVE_CMD" <<\'PY\'')
+                runner_lines.append('import shlex, sys')
+                runner_lines.append('parts = shlex.split(sys.argv[1])')
+                runner_lines.append('patch = r"""import inspect, sys')
+                runner_lines.append('from vllm.engine.arg_utils import EngineArgs, AsyncEngineArgs')
+                runner_lines.append('def _odysseus_swap0(cls):')
+                runner_lines.append('    params = list(inspect.signature(cls).parameters)')
+                runner_lines.append('    if "swap_space" not in params:')
+                runner_lines.append('        return')
+                runner_lines.append('    idx = params.index("swap_space")')
+                runner_lines.append('    defaults = list(cls.__init__.__defaults__ or ())')
+                runner_lines.append('    if idx < len(defaults):')
+                runner_lines.append('        defaults[idx] = 0')
+                runner_lines.append('        cls.__init__.__defaults__ = tuple(defaults)')
+                runner_lines.append('    fields = getattr(cls, "__dataclass_fields__", {})')
+                runner_lines.append('    if "swap_space" in fields:')
+                runner_lines.append('        fields["swap_space"].default = 0')
+                runner_lines.append('_odysseus_swap0(EngineArgs)')
+                runner_lines.append('_odysseus_swap0(AsyncEngineArgs)')
+                runner_lines.append('try:')
+                runner_lines.append('    from vllm.config import CacheConfig')
+                runner_lines.append('    CacheConfig.swap_space = 0')
+                runner_lines.append('except Exception:')
+                runner_lines.append('    pass')
+                runner_lines.append('_orig_create_engine_config = EngineArgs.create_engine_config')
+                runner_lines.append('def _odysseus_create_engine_config(self, *args, **kwargs):')
+                runner_lines.append('    self.swap_space = 0')
+                runner_lines.append('    return _orig_create_engine_config(self, *args, **kwargs)')
+                runner_lines.append('EngineArgs.create_engine_config = _odysseus_create_engine_config')
+                runner_lines.append('AsyncEngineArgs.create_engine_config = _odysseus_create_engine_config')
+                runner_lines.append('from vllm.entrypoints.cli.main import main')
+                runner_lines.append('sys.exit(main())"""')
+                runner_lines.append('try:')
+                runner_lines.append('    serve_i = parts.index("serve")')
+                runner_lines.append('except ValueError:')
+                runner_lines.append('    print(shlex.join(parts))')
+                runner_lines.append('else:')
+                runner_lines.append('    exe_i = serve_i - 1')
+                runner_lines.append('    exe = parts[exe_i] if exe_i >= 0 else "vllm"')
+                runner_lines.append('    py = "python3"')
+                runner_lines.append('    if exe.endswith("/bin/vllm"):')
+                runner_lines.append('        py = exe[:-len("/bin/vllm")] + "/bin/python"')
+                runner_lines.append('    parts[exe_i:serve_i] = [py, "-c", patch]')
+                runner_lines.append('    print(shlex.join(parts))')
+                runner_lines.append('PY')
+                runner_lines.append(')"')
+                runner_lines.append('  echo "[odysseus] Patched vLLM internal swap_space default to 0 for this runtime."')
+                runner_lines.append('fi')
             elif "sglang.launch_server" in req.cmd:
                 runner_lines.append('export PATH="$HOME/.local/bin:$PATH"')
                 runner_lines.append('if ! command -v sglang &>/dev/null; then')
@@ -1620,7 +1783,10 @@ def setup_cookbook_routes() -> APIRouter:
                     runner_lines,
                     keep_shell_open=not local_windows,
                 )
-                runner_lines.append(req.cmd)
+                if "vllm serve" in req.cmd:
+                    runner_lines.append('eval "$ODYSSEUS_SERVE_CMD"')
+                else:
+                    runner_lines.append(req.cmd)
                 if local_windows:
                     # Detached background process — no interactive shell to keep open.
                     # Print the exit marker the status poller looks for, then stop.
@@ -2418,16 +2584,14 @@ def setup_cookbook_routes() -> APIRouter:
             # Add 30% headroom for KV cache, activations, etc.
             needed_vram = (est_vram * 1.3) if est_vram else None
 
-            if vram_gb > 0 and needed_vram is not None and needed_vram > vram_gb:
-                continue
-            # Unknown-size models (e.g. MiniMax-M2.7, DeepSeek-V4-Flash) have no
-            # "NB" in the repo id, so the regex above can't extract their
-            # param count. Previously we dropped them entirely, which made
-            # brand-new flagship releases silently vanish from this list even
-            # on rigs with hundreds of GB of VRAM. Adapters/LoRAs are already
-            # filtered by _is_excluded(), so what falls through here is
-            # overwhelmingly full models — keep them, just without a size
-            # badge (the frontend handles needed_vram_gb=null gracefully).
+            if vram_gb > 0:
+                if needed_vram is None:
+                    # The "trending models that fit" list must be conservative:
+                    # if we cannot estimate size from the repo id/tags, do not
+                    # present it as runnable on this hardware.
+                    continue
+                if needed_vram > vram_gb:
+                    continue
 
             out.append({
                 "repo_id": repo_id,
@@ -2624,6 +2788,32 @@ def setup_cookbook_routes() -> APIRouter:
             except Exception as e:
                 logger.warning(f"orphan sweep: state write failed: {e}")
 
+    @router.get("/api/cookbook/hf-gguf-files")
+    async def hf_gguf_files(repo_id: str, owner: str = Depends(require_user)):
+        """List GGUF files in a HuggingFace repo for the direct-download picker."""
+        import httpx
+
+        repo_id = _validate_repo_id(repo_id)
+        url = f"https://huggingface.co/api/models/{repo_id}"
+        try:
+            headers = {}
+            token = _load_stored_hf_token()
+            if token:
+                headers["Authorization"] = f"Bearer {token}"
+            async with httpx.AsyncClient(timeout=15, follow_redirects=True) as client:
+                resp = await client.get(url, headers=headers)
+                if resp.status_code != 200:
+                    return {"ok": False, "files": [], "error": f"HF API HTTP {resp.status_code}"}
+                data = resp.json()
+        except Exception as e:
+            return {"ok": False, "files": [], "error": str(e)}
+        files = [
+            str(s.get("rfilename") or "")
+            for s in data.get("siblings", [])
+            if str(s.get("rfilename") or "").lower().endswith(".gguf")
+        ]
+        return {"ok": True, "repo_id": repo_id, "files": files}
+
     # In-memory cache for the Ollama library scrape. ollama.com is a public
     # site, but it doesn't expose a stable JSON listing — we fetch the HTML
     # search page and regex out the model cards. Cached for 1 h so a busy

routes/email_helpers.py

@@ -1109,22 +1109,30 @@ def _list_attachments_from_msg(msg):
         return attachments
     idx = 0
     for part in msg.walk():
-        if part.is_multipart():
-            continue
         cd = str(part.get("Content-Disposition", ""))
         ct = part.get_content_type()
+        is_attached_email = ct == "message/rfc822" and ("attachment" in cd.lower() or part.get_filename())
+        if part.is_multipart() and not is_attached_email:
+            continue
         # Skip text/html body parts (only consider real attachments)
         if ct in ("text/plain", "text/html") and "attachment" not in cd:
             continue
         filename = part.get_filename()
         if filename:
             filename = _decode_header(filename)
+            if ct == "message/rfc822" and not re.search(r"\.[A-Za-z0-9]{1,8}$", filename):
+                filename = f"{filename}.eml"
         else:
             # Inline images, etc. - generate a name
-            ext = ct.split("/")[-1] if "/" in ct else "bin"
+            ext = "eml" if ct == "message/rfc822" else (ct.split("/")[-1] if "/" in ct else "bin")
             filename = f"attachment_{idx}.{ext}"
         payload = part.get_payload(decode=True)
-        size = len(payload) if payload else 0
+        if payload is None and ct == "message/rfc822":
+            try:
+                payload = part.as_bytes()
+            except Exception:
+                payload = b""
+        size = len(payload) if payload is not None else 0
         attachments.append({
             "index": idx,
             "filename": filename,
@@ -1136,29 +1144,58 @@ def _list_attachments_from_msg(msg):
     return attachments
 
 
+def _is_likely_signature_image_attachment(att: dict) -> bool:
+    """Match the reader's inline signature/logo image filter."""
+    filename = str((att or {}).get("filename") or "").lower()
+    if not re.search(r"\.(png|jpe?g|gif|bmp|svg|webp)$", filename):
+        return False
+    size = int((att or {}).get("size") or 0)
+    if re.search(r"^image\d{3,}\.(png|jpe?g|gif)$", filename):
+        return True
+    if re.search(r"^(signature|logo|sig|footer|banner)[-_\d]*\.(png|jpe?g|gif|svg)$", filename):
+        return True
+    return 0 < size < 30 * 1024
+
+
+def _has_visible_attachments(msg) -> bool:
+    """Return True only for attachments the reader will render as chips."""
+    return any(
+        not _is_likely_signature_image_attachment(att)
+        for att in _list_attachments_from_msg(msg)
+    )
+
+
 def _extract_attachment_to_disk(msg, index, target_dir):
     """Extract a specific attachment to disk and return the file path."""
     if not msg.is_multipart():
         return None
     idx = 0
     for part in msg.walk():
-        if part.is_multipart():
-            continue
         cd = str(part.get("Content-Disposition", ""))
         ct = part.get_content_type()
+        is_attached_email = ct == "message/rfc822" and ("attachment" in cd.lower() or part.get_filename())
+        if part.is_multipart() and not is_attached_email:
+            continue
         if ct in ("text/plain", "text/html") and "attachment" not in cd:
             continue
         if idx == index:
             filename = part.get_filename()
             if filename:
                 filename = _decode_header(filename)
+                if ct == "message/rfc822" and not re.search(r"\.[A-Za-z0-9]{1,8}$", filename):
+                    filename = f"{filename}.eml"
             else:
-                ext = ct.split("/")[-1] if "/" in ct else "bin"
+                ext = "eml" if ct == "message/rfc822" else (ct.split("/")[-1] if "/" in ct else "bin")
                 filename = f"attachment_{idx}.{ext}"
             # Sanitize
             safe_name = re.sub(r"[^\w\s\-.]", "_", filename).strip()
             payload = part.get_payload(decode=True)
-            if not payload:
+            if payload is None and ct == "message/rfc822":
+                try:
+                    payload = part.as_bytes()
+                except Exception:
+                    payload = b""
+            if payload is None:
                 return None
             target_dir.mkdir(parents=True, exist_ok=True)
             filepath = target_dir / safe_name

routes/email_routes.py

@@ -44,7 +44,7 @@ from routes.email_helpers import (
     _send_smtp_message, _smtp_security_mode,
     _IMAP_TIMEOUT_SECONDS, _open_imap_connection,
     _imap_connect, _imap, _decode_header, _detect_sent_folder, _detect_drafts_folder,
-    _extract_attachment_text, _list_attachments_from_msg,
+    _extract_attachment_text, _list_attachments_from_msg, _has_visible_attachments, _is_likely_signature_image_attachment,
     _extract_attachment_to_disk, _extract_html, _extract_text,
     _fetch_sender_thread_context, _pre_retrieve_context,
     _EMAIL_REPLY_SYS_PROMPT_BASE, _POOL_HOOKS,
@@ -58,6 +58,7 @@ from routes.email_pollers import _start_poller
 logger = logging.getLogger(__name__)
 
 ODYSSEUS_MAIL_ORIGIN = "odysseus-ui"
+EMAIL_READ_ATTACHMENT_VERSION = 2
 
 
 def _email_tag_owner_aliases(account_id: str | None, owner: str = "") -> list[str]:
@@ -244,6 +245,21 @@ def _imap_uid_fetch(conn, uid_set: str | bytes, query: str):
     return conn.uid("FETCH", _uid_bytes(uid_set), query)
 
 
+def _imap_search_quote(value: str) -> str:
+    return '"' + str(value or "").replace("\\", "\\\\").replace('"', '\\"') + '"'
+
+
+def _message_id_chain(*values: str) -> list[str]:
+    seen = set()
+    out = []
+    for value in values:
+        for mid in re.findall(r"<[^>]+>", value or ""):
+            if mid not in seen:
+                seen.add(mid)
+                out.append(mid)
+    return out
+
+
 def _uid_from_fetch_meta(meta_b: bytes) -> str:
     m = re.search(rb"\bUID\s+(\d+)\b", meta_b)
     return m.group(1).decode() if m else ""
@@ -1003,6 +1019,65 @@ def setup_email_routes():
                 except Exception:
                     pass
 
+    def _related_thread_attachments_sync(
+        folder: str,
+        account_id: str | None,
+        owner: str,
+        current_uid: str,
+        current_message_id: str,
+        in_reply_to: str,
+        references: str,
+        limit: int = 12,
+    ) -> list[dict]:
+        """Return visible attachments from referenced messages in this folder."""
+        wanted_ids = _message_id_chain(references, in_reply_to)
+        current_mid = (current_message_id or "").strip()
+        wanted_ids = [mid for mid in wanted_ids if mid and mid != current_mid]
+        if not wanted_ids:
+            return []
+
+        related: list[dict] = []
+        try:
+            with _imap(account_id, owner=owner) as conn:
+                conn.select(_q(folder), readonly=True)
+                # Search newest referenced messages first; cap work so opening
+                # a long thread stays bounded.
+                for mid in reversed(wanted_ids[-10:]):
+                    if len(related) >= limit:
+                        break
+                    status, data = _imap_uid_search(conn, f'(HEADER Message-ID {_imap_search_quote(mid)})')
+                    if status != "OK" or not data or not data[0]:
+                        continue
+                    for uid_b in reversed(data[0].split()[-3:]):
+                        source_uid = uid_b.decode(errors="ignore")
+                        if not source_uid or source_uid == str(current_uid):
+                            continue
+                        st2, msg_data = _imap_uid_fetch(conn, source_uid, "(BODY.PEEK[])")
+                        if st2 != "OK" or not msg_data or not isinstance(msg_data[0], tuple):
+                            continue
+                        msg = email_mod.message_from_bytes(msg_data[0][1])
+                        source_from = _decode_header(msg.get("From", ""))
+                        source_subject = _decode_header(msg.get("Subject", ""))
+                        source_date = msg.get("Date", "")
+                        for att in _list_attachments_from_msg(msg):
+                            if _is_likely_signature_image_attachment(att):
+                                continue
+                            enriched = dict(att)
+                            enriched.update({
+                                "source_uid": source_uid,
+                                "source_folder": folder,
+                                "source_message_id": (msg.get("Message-ID") or "").strip(),
+                                "source_from": source_from,
+                                "source_subject": source_subject,
+                                "source_date": source_date,
+                            })
+                            related.append(enriched)
+                            if len(related) >= limit:
+                                break
+        except Exception as e:
+            logger.debug(f"related thread attachment lookup failed uid={current_uid}: {e}")
+        return related
+
     @router.get("/list")
     async def list_emails(
         folder: str = Query("INBOX"),
@@ -1273,6 +1348,17 @@ def setup_email_routes():
             sender_name, sender_addr = email.utils.parseaddr(sender)
             parsed_date = email.utils.parsedate_to_datetime(date_str) if date_str else None
             attachments = _list_attachments_from_msg(msg)
+            related_attachments = []
+            if not _has_visible_attachments(msg):
+                related_attachments = _related_thread_attachments_sync(
+                    folder,
+                    account_id,
+                    owner,
+                    uid,
+                    message_id,
+                    in_reply_to,
+                    references,
+                )
 
             if mark_seen:
                 # Set \Seen in a separate readwrite session so concurrent reads
@@ -1381,6 +1467,8 @@ def setup_email_routes():
                 "body": body,
                 "body_html": body_html,
                 "attachments": attachments,
+                "related_attachments": related_attachments,
+                "attachment_version": EMAIL_READ_ATTACHMENT_VERSION,
                 "cached_summary": cached_summary,
                 "cached_ai_reply": cached_ai_reply,
                 "boundaries": cached_boundaries,
@@ -1411,6 +1499,12 @@ def setup_email_routes():
         """Read email body. Cached for 30m, sync IMAP work runs in a thread."""
         ck = _read_cache_key(account_id, folder, uid, owner=owner)
         cached = _read_cache_get(ck)
+        if cached is not None:
+            # Older cached read responses lack the thread-attachment fallback.
+            # Fetch once so replies that reference prior attachments can show
+            # those files without waiting for cache expiry.
+            if cached.get("attachment_version") != EMAIL_READ_ATTACHMENT_VERSION:
+                cached = None
         if cached is not None:
             if mark_seen:
                 try:
@@ -1599,6 +1693,65 @@ def setup_email_routes():
                     return None
             doc_session_id = _resolve_doc_session()
 
+            def _create_markdown_doc(content: str, summary: str):
+                from src.database import SessionLocal as _SL, Document as _Doc, DocumentVersion as _DV
+                doc_id = str(uuid.uuid4())
+                ver_id = str(uuid.uuid4())
+                _db = _SL()
+                try:
+                    _db.query(_Doc).filter(_Doc.is_active == True).update({"is_active": False})
+                    _db.add(_Doc(
+                        id=doc_id, session_id=doc_session_id, title=title,
+                        language="markdown", current_content=content,
+                        version_count=1, is_active=True,
+                    ))
+                    _db.add(_DV(
+                        id=ver_id, document_id=doc_id, version_number=1,
+                        content=content, summary=summary, source="upload",
+                    ))
+                    _db.commit()
+                finally:
+                    _db.close()
+                _tag_doc_with_source(doc_id)
+                return doc_id
+
+            def _attached_email_markdown(path):
+                raw_bytes = path.read_bytes()
+                if not raw_bytes:
+                    return f"# Attached email: {base}\n\n_(empty email attachment)_"
+                try:
+                    attached_msg = email_mod.message_from_bytes(raw_bytes)
+                except Exception as e:
+                    return f"# Attached email: {base}\n\nCould not parse this email attachment: {e}"
+
+                attached_subject = _decode_header(attached_msg.get("Subject", "")) or base
+                attached_from = _decode_header(attached_msg.get("From", ""))
+                attached_to = _decode_header(attached_msg.get("To", ""))
+                attached_cc = _decode_header(attached_msg.get("Cc", ""))
+                attached_date = attached_msg.get("Date", "")
+                attached_body = _extract_text(attached_msg).strip()
+                attached_atts = _list_attachments_from_msg(attached_msg)
+
+                lines = [f"# Attached email: {attached_subject}", ""]
+                if attached_from:
+                    lines.append(f"**From:** {attached_from}")
+                if attached_to:
+                    lines.append(f"**To:** {attached_to}")
+                if attached_cc:
+                    lines.append(f"**Cc:** {attached_cc}")
+                if attached_date:
+                    lines.append(f"**Date:** {attached_date}")
+                lines.extend(["", "## Body", "", attached_body or "_(no readable body)_"])
+                if attached_atts:
+                    lines.extend(["", "## Attachments", ""])
+                    for att in attached_atts:
+                        size = int(att.get("size") or 0)
+                        size_label = f"{size} B" if size < 1024 else f"{round(size / 1024)} KB"
+                        name = att.get("filename") or f"attachment_{att.get('index', '')}"
+                        ctype = att.get("content_type") or "application/octet-stream"
+                        lines.append(f"- {name} ({ctype}, {size_label})")
+                return "\n".join(lines).strip()
+
             # ── PDF path (existing) ────────────────────────────────────
             if ext == ".pdf":
                 import shutil as _shutil
@@ -1645,6 +1798,15 @@ def setup_email_routes():
                 _tag_doc_with_source(doc_id)
                 return {"doc_id": doc_id, "filename": filepath.name}
 
+            # ── Attached email (.eml / message/rfc822) ────────────────
+            if ext == ".eml":
+                try:
+                    content = _attached_email_markdown(filepath)
+                except Exception as e:
+                    return {"error": f"Failed to read email attachment: {e}", "filename": base}
+                doc_id = _create_markdown_doc(content, "Imported attached email")
+                return {"doc_id": doc_id, "filename": filepath.name}
+
             # ── DOCX path: extract text → markdown document ───────────
             if ext == ".docx":
                 try:
@@ -1682,25 +1844,7 @@ def setup_email_routes():
                     lines.append("")
                 content = "\n".join(lines).strip() or f"_(empty {base})_"
 
-                from src.database import SessionLocal as _SL, Document as _Doc, DocumentVersion as _DV
-                doc_id = str(uuid.uuid4())
-                ver_id = str(uuid.uuid4())
-                _db = _SL()
-                try:
-                    _db.query(_Doc).filter(_Doc.is_active == True).update({"is_active": False})
-                    _db.add(_Doc(
-                        id=doc_id, session_id=doc_session_id, title=title,
-                        language="markdown", current_content=content,
-                        version_count=1, is_active=True,
-                    ))
-                    _db.add(_DV(
-                        id=ver_id, document_id=doc_id, version_number=1,
-                        content=content, summary="Imported from DOCX", source="upload",
-                    ))
-                    _db.commit()
-                finally:
-                    _db.close()
-                _tag_doc_with_source(doc_id)
+                doc_id = _create_markdown_doc(content, "Imported from DOCX")
                 return {"doc_id": doc_id, "filename": filepath.name}
 
             # ── Plain text / markdown ────────────────────────────────
@@ -1709,25 +1853,7 @@ def setup_email_routes():
                     content = filepath.read_text(encoding="utf-8", errors="replace")
                 except Exception as e:
                     return {"error": f"Failed to read text file: {e}", "filename": base}
-                from src.database import SessionLocal as _SL, Document as _Doc, DocumentVersion as _DV
-                doc_id = str(uuid.uuid4())
-                ver_id = str(uuid.uuid4())
-                _db = _SL()
-                try:
-                    _db.query(_Doc).filter(_Doc.is_active == True).update({"is_active": False})
-                    _db.add(_Doc(
-                        id=doc_id, session_id=doc_session_id, title=title,
-                        language="markdown", current_content=content,
-                        version_count=1, is_active=True,
-                    ))
-                    _db.add(_DV(
-                        id=ver_id, document_id=doc_id, version_number=1,
-                        content=content, summary="Imported from email attachment", source="upload",
-                    ))
-                    _db.commit()
-                finally:
-                    _db.close()
-                _tag_doc_with_source(doc_id)
+                doc_id = _create_markdown_doc(content, "Imported from email attachment")
                 return {"doc_id": doc_id, "filename": filepath.name}
 
             return {"error": f"Unsupported attachment type: {ext}", "filename": base}

routes/hwfit_routes.py

@@ -1,8 +1,13 @@
+import json
+import os
 import re
+import shlex
+import subprocess
 from copy import deepcopy
 
 from fastapi import APIRouter, HTTPException
 
+from core.platform_compat import run_ssh_command
 from routes._validators import validate_remote_host, validate_ssh_port
 
 
@@ -107,6 +112,73 @@ def _apply_manual_hardware(system, manual_mode="", manual_gpu_count="", manual_v
     return system
 
 
+def _run_model_probe(host: str, ssh_port: str, cmd: str) -> str:
+    try:
+        if host:
+            r = run_ssh_command(
+                host,
+                ssh_port or None,
+                cmd,
+                timeout=15,
+                connect_timeout=5,
+                strict_host_key_checking=False,
+                text=True,
+            )
+        else:
+            r = subprocess.run(["bash", "-lc", cmd], capture_output=True, text=True, timeout=15)
+        if r.returncode == 0:
+            return (r.stdout or "").strip()
+    except Exception:
+        return ""
+    return ""
+
+
+def _inspect_model_path(model_path: str, host: str = "", ssh_port: str = "") -> dict:
+    """Read lightweight metadata from a local or SSH-visible HF model folder."""
+    path = (model_path or "").strip()
+    if not path or path.startswith(("http://", "https://")):
+        return {}
+    if not (path.startswith("/") or path.startswith("~")):
+        return {}
+
+    qpath = shlex.quote(path)
+    qconfig = shlex.quote(os.path.join(path, "config.json"))
+    out = {}
+    exists = _run_model_probe(host, ssh_port, f"test -d {qpath} && printf found || printf missing")
+    if exists != "found":
+        target = host or "local container"
+        out["model_probe_error"] = f"Model path is not visible on {target}: {path}"
+        return out
+    raw_config = _run_model_probe(host, ssh_port, f"test -f {qconfig} && sed -n '1,240p' {qconfig}")
+    if raw_config:
+        try:
+            cfg = json.loads(raw_config)
+        except Exception:
+            cfg = {}
+        for key in ("context_length", "max_position_embeddings", "n_ctx_train", "model_max_length", "max_seq_len"):
+            value = cfg.get(key)
+            if isinstance(value, (int, float)) and value > 0:
+                out["model_ctx_max"] = int(value)
+                break
+    else:
+        out["model_probe_error"] = f"config.json not found in model path: {path}"
+
+    size_cmd = (
+        f"find {qpath} -type f \\( -name '*.safetensors' -o -name '*.bin' -o -name '*.gguf' \\) "
+        "-printf '%s\\n' 2>/dev/null | awk '{s+=$1} END {if (s>0) printf \"%.6f\", s/1073741824}'"
+    )
+    weights = _run_model_probe(host, ssh_port, size_cmd)
+    try:
+        weights_gb = float(weights)
+    except Exception:
+        weights_gb = 0.0
+    if weights_gb > 0:
+        out["model_weights_gb"] = round(weights_gb, 3)
+    elif "model_probe_error" not in out:
+        out["model_probe_error"] = f"No model weight files found in: {path}"
+    return out
+
+
 def setup_hwfit_routes():
     router = APIRouter(prefix="/api/hwfit", tags=["hwfit"])
 
@@ -235,7 +307,7 @@ def setup_hwfit_routes():
         return {"system": system, "models": results}
 
     @router.get("/profiles")
-    def get_serve_profiles(model: str = "", host: str = "", ssh_port: str = "", platform: str = "", fresh: bool = False, serve_weights_gb: float = 0.0, serve_quant: str = ""):
+    def get_serve_profiles(model: str = "", model_path: str = "", host: str = "", ssh_port: str = "", platform: str = "", fresh: bool = False, serve_weights_gb: float = 0.0, serve_quant: str = ""):
         """Compute llama.cpp serve profiles (Quality/Balanced/Speed) for `model`
         against the detected hardware on `host` (or local). Returns concrete
         flags (n_gpu_layers, n_cpu_moe, cache_type, ctx) the serve UI can apply.
@@ -272,8 +344,16 @@ def setup_hwfit_routes():
                 if nn and (nn == want or want.endswith(nn) or nn.endswith(want)):
                     m = entry
                     break
+        path_meta = _inspect_model_path(model_path or model, host=host, ssh_port=ssh_port)
         if m is None:
-            return {"system": system, "profiles": [], "error": "model not in catalog"}
+            return {
+                "system": system,
+                "profiles": [],
+                "error": "model not in catalog",
+                "model_ctx_max": int(path_meta.get("model_ctx_max") or 0),
+                "model_weights_gb": float(path_meta.get("model_weights_gb") or 0),
+                "model_probe_error": path_meta.get("model_probe_error") or "",
+            }
         # Surface the model's trained context limit so the serve UI can clamp a
         # user-typed context down to it (asking for ctx > n_ctx_train overflows
         # and, with a quantized KV cache, can crash the GPU).
@@ -283,6 +363,16 @@ def setup_hwfit_routes():
             if isinstance(v, (int, float)) and v > 0:
                 model_ctx_max = int(v)
                 break
+        path_ctx_max = int(path_meta.get("model_ctx_max") or 0)
+        if path_ctx_max > 0:
+            model_ctx_max = max(model_ctx_max, path_ctx_max)
+        model_weights_gb = float(path_meta.get("model_weights_gb") or 0)
+        if model_weights_gb <= 0:
+            for k in ("min_vram_gb", "required_gb", "size_gb", "recommended_ram_gb", "min_ram_gb"):
+                v = m.get(k)
+                if isinstance(v, (int, float)) and v > 0:
+                    model_weights_gb = float(v)
+                    break
         return {
             "system": system,
             "profiles": compute_serve_profiles(
@@ -291,6 +381,8 @@ def setup_hwfit_routes():
                 serve_quant=(serve_quant or None),
             ),
             "model_ctx_max": model_ctx_max,
+            "model_weights_gb": model_weights_gb,
+            "model_probe_error": path_meta.get("model_probe_error") or "",
         }
 
     @router.get("/image-models")

routes/model_routes.py

@@ -1064,9 +1064,11 @@ def setup_model_routes(model_discovery):
         except Exception:
             return 0.0
 
-    def _failure_delay(fails: int) -> float:
+    def _failure_delay(fails: int, *, empty_local: bool = False) -> float:
         if fails <= 0:
             return 0.0
+        if empty_local:
+            return min(5.0 * (2 ** max(0, fails - 1)), 30.0)
         return min(_REFRESH_FAILURE_BASE * (2 ** max(0, fails - 1)), _REFRESH_FAILURE_MAX)
 
     def _should_refresh_endpoint(ep: Any, now: float, force: bool = False) -> tuple[bool, Dict[str, Any]]:
@@ -1097,7 +1099,12 @@ def setup_model_routes(model_discovery):
         fails = int(state.get("fail_count") or 0)
         if fails and not force:
             last_failure = float(state.get("last_failure") or 0.0)
-            if now - last_failure < _failure_delay(fails):
+            empty_local = (
+                not cached
+                and category == "local"
+                and str(getattr(ep, "id", "") or "").startswith("local-")
+            )
+            if now - last_failure < _failure_delay(fails, empty_local=empty_local):
                 return False, info
         if cached and not force:
             interval = _endpoint_refresh_interval(ep, category)

routes/shell_routes.py

@@ -330,6 +330,9 @@ def add_user_install_bins_to_path():
         candidates.append(os.path.join(site.USER_BASE, 'bin'))
     except Exception:
         pass
+    candidates.append(os.path.expanduser('~/bin'))
+    candidates.append(os.path.expanduser('~/llama.cpp/build/bin'))
+    candidates.append(os.path.expanduser('~/llama.cpp/build-vulkan/bin'))
     candidates.append(os.path.expanduser('~/.local/bin'))
     parts = os.environ.get('PATH', '').split(os.pathsep) if os.environ.get('PATH') else []
     changed = False
@@ -1188,6 +1191,7 @@ def setup_shell_routes() -> APIRouter:
         # venv over SSH so a remote `pip install` actually reflects here.
         remote_status: dict = {}
         remote_details: dict = {}
+        remote_probe_error = ""
         remote_names = [
             p["name"]
             for p in packages
@@ -1226,8 +1230,34 @@ def setup_shell_routes() -> APIRouter:
                         break
             except ValueError as e:
                 raise HTTPException(400, str(e))
-            except Exception:
+            except Exception as e:
                 remote_status = {}
+                remote_probe_error = f"SSH package probe failed: {str(e)[:160]}"
+            if "llama_cpp" in remote_names:
+                try:
+                    inner = (
+                        'export PATH="$HOME/.local/bin:$HOME/bin:'
+                        '$HOME/llama.cpp/build/bin:$HOME/llama.cpp/build-vulkan/bin:$PATH"; '
+                        "command -v llama-server 2>/dev/null || true"
+                    )
+                    argv = _ssh_base_argv(host, ssh_port) + [inner]
+                    proc = await asyncio.create_subprocess_exec(
+                        *argv,
+                        stdout=asyncio.subprocess.PIPE,
+                        stderr=asyncio.subprocess.PIPE,
+                    )
+                    out, _err = await asyncio.wait_for(proc.communicate(), timeout=8)
+                    llama_server_path = out.decode("utf-8", errors="replace").strip().splitlines()
+                    llama_server_path = llama_server_path[-1].strip() if llama_server_path else ""
+                    if llama_server_path:
+                        remote_status["llama_cpp"] = True
+                        probe = remote_details.setdefault("llama_cpp", {})
+                        if isinstance(probe, dict):
+                            probe.setdefault("binaries", {})["llama-server"] = llama_server_path
+                except Exception as e:
+                    if not remote_probe_error:
+                        remote_probe_error = f"SSH llama-server probe failed: {str(e)[:160]}"
+                    pass
         # Union of system_names + every package's system_prereqs. Probing
         # the prereqs alongside the main system deps in a single SSH call
         # avoids a second round-trip per Cookbook → Dependencies refresh.
@@ -1272,7 +1302,9 @@ def setup_shell_routes() -> APIRouter:
                 target_os_id = _os_id_from_release("\n".join(_osrel_lines))
             except ValueError as e:
                 raise HTTPException(400, str(e))
-            except Exception:
+            except Exception as e:
+                if not remote_probe_error:
+                    remote_probe_error = f"SSH system probe failed: {str(e)[:160]}"
                 pass
         elif not host:
             # Local target — probe in-process so the inline install command
@@ -1290,7 +1322,12 @@ def setup_shell_routes() -> APIRouter:
             on_remote = bool(host and pkg.get("target") == "remote")
             probe = None
             if on_remote:
-                pkg["installed"] = bool(remote_status.get(pkg["name"], False))
+                if remote_probe_error and pkg["name"] not in remote_status:
+                    pkg["installed"] = None
+                    pkg["probe_error"] = remote_probe_error
+                    pkg["status_note"] = remote_probe_error
+                else:
+                    pkg["installed"] = bool(remote_status.get(pkg["name"], False))
                 probe = remote_details.get(pkg["name"])
                 if isinstance(probe, dict):
                     pkg["details"] = probe
@@ -1353,9 +1390,19 @@ def setup_shell_routes() -> APIRouter:
             # reads "ready" green while inference runs at 3 tok/s on GPU
             # silicon — actively misleading.
             if pkg["name"] == "llama_cpp" and pkg.get("installed"):
+                _native_llama_server = bool(
+                    isinstance(probe, dict)
+                    and isinstance(probe.get("binaries"), dict)
+                    and probe["binaries"].get("llama-server")
+                )
                 _gpu_capable = False
                 _has_nvidia_target = False
-                if on_remote and host:
+                if _native_llama_server:
+                    # Native llama-server is the launcher path Cookbook now
+                    # prefers. Do not mark this as a CPU-only Python wheel just
+                    # because llama-cpp-python is absent from the selected venv.
+                    _gpu_capable = True
+                elif on_remote and host:
                     try:
                         # Activate the configured venv FIRST so the probe
                         # runs against the same python the launch script
@@ -1609,7 +1656,8 @@ def setup_shell_routes() -> APIRouter:
             return {"ok": False, "error": f"Unsupported engine: {engine}"}
         host = str(body.get("remote_host") or "").strip()
         ssh_port = body.get("ssh_port")
-        cmd = _llama_cpp_rebuild_cmd()
+        update_source = bool(body.get("update_source"))
+        cmd = _llama_cpp_rebuild_cmd(update_source=update_source)
         try:
             argv = (
                 (_ssh_base_argv(host, ssh_port) + [cmd])