Merge branch 'NousResearch:main' into fix/openviking-viking-read-file-uri

plugins/disk-cleanup/README.md

@@ -0,0 +1,51 @@
+# disk-cleanup
+
+Auto-tracks and cleans up ephemeral files created during Hermes Agent
+sessions — test scripts, temp outputs, cron logs, stale chrome profiles.
+Scoped strictly to `$HERMES_HOME` and `/tmp/hermes-*`.
+
+Originally contributed by [@LVT382009](https://github.com/LVT382009) as a
+skill in PR #12212.  Ported to the plugin system so the behaviour runs
+automatically via `post_tool_call` and `on_session_end` hooks — the agent
+never needs to remember to call a tool.
+
+## How it works
+
+| Hook | Behaviour |
+|---|---|
+| `post_tool_call` | When `write_file` / `terminal` / `patch` creates a file matching `test_*`, `tmp_*`, or `*.test.*` inside `HERMES_HOME`, track it silently as `test` / `temp` / `cron-output`. |
+| `on_session_end` | If any test files were auto-tracked during this turn, run `quick` cleanup (no prompts). |
+
+Deletion rules (same as the original PR):
+
+| Category | Threshold | Confirmation |
+|---|---|---|
+| `test` | every session end | Never |
+| `temp` | >7 days since tracked | Never |
+| `cron-output` | >14 days since tracked | Never |
+| empty dirs under HERMES_HOME | always | Never |
+| `research` | >30 days, beyond 10 newest | Always (deep only) |
+| `chrome-profile` | >14 days since tracked | Always (deep only) |
+| files >500 MB | never auto | Always (deep only) |
+
+## Slash command
+
+```
+/disk-cleanup status                     # breakdown + top-10 largest
+/disk-cleanup dry-run                    # preview without deleting
+/disk-cleanup quick                      # run safe cleanup now
+/disk-cleanup deep                       # quick + list items needing prompt
+/disk-cleanup track <path> <category>    # manual tracking
+/disk-cleanup forget <path>              # stop tracking
+```
+
+## Safety
+
+- `is_safe_path()` rejects anything outside `HERMES_HOME` or `/tmp/hermes-*`
+- Windows mounts (`/mnt/c` etc.) are rejected
+- The state directory `$HERMES_HOME/disk-cleanup/` is itself excluded
+- `$HERMES_HOME/logs/`, `memories/`, `sessions/`, `skills/`, `plugins/`,
+  and config files are never tracked
+- Backup/restore is scoped to `tracked.json` — the plugin never touches
+  agent logs
+- Atomic writes: `.tmp` → backup → rename

plugins/disk-cleanup/__init__.py

@@ -0,0 +1,316 @@
+"""disk-cleanup plugin — auto-cleanup of ephemeral Hermes session files.
+
+Wires three behaviours:
+
+1. ``post_tool_call`` hook — inspects ``write_file`` and ``terminal``
+   tool results for newly-created paths matching test/temp patterns
+   under ``HERMES_HOME`` and tracks them silently.  Zero agent
+   compliance required.
+
+2. ``on_session_end`` hook — when any test files were auto-tracked
+   during the just-finished turn, runs :func:`disk_cleanup.quick` and
+   logs a single line to ``$HERMES_HOME/disk-cleanup/cleanup.log``.
+
+3. ``/disk-cleanup`` slash command — manual ``status``, ``dry-run``,
+   ``quick``, ``deep``, ``track``, ``forget``.
+
+Replaces PR #12212's skill-plus-script design: the agent no longer
+needs to remember to run commands.
+"""
+
+from __future__ import annotations
+
+import logging
+import re
+import shlex
+import threading
+from pathlib import Path
+from typing import Any, Dict, Optional, Set
+
+from . import disk_cleanup as dg
+
+logger = logging.getLogger(__name__)
+
+
+# Per-task set of "test files newly tracked this turn".  Keyed by task_id
+# (or session_id as fallback) so on_session_end can decide whether to run
+# cleanup.  Guarded by a lock — post_tool_call can fire concurrently on
+# parallel tool calls.
+_recent_test_tracks: Dict[str, Set[str]] = {}
+_lock = threading.Lock()
+
+
+# Tool-call result shapes we can parse
+_WRITE_FILE_PATH_KEY = "path"
+_TERMINAL_PATH_REGEX = re.compile(r"(?:^|\s)(/[^\s'\"`]+|\~/[^\s'\"`]+)")
+
+
+# ---------------------------------------------------------------------------
+# Helpers
+# ---------------------------------------------------------------------------
+
+def _tracker_key(task_id: str, session_id: str) -> str:
+    return task_id or session_id or "default"
+
+
+def _record_track(task_id: str, session_id: str, path: Path, category: str) -> None:
+    """Record that we tracked *path* as *category* during this turn."""
+    if category != "test":
+        return
+    key = _tracker_key(task_id, session_id)
+    with _lock:
+        _recent_test_tracks.setdefault(key, set()).add(str(path))
+
+
+def _drain(task_id: str, session_id: str) -> Set[str]:
+    """Pop the set of test paths tracked during this turn."""
+    key = _tracker_key(task_id, session_id)
+    with _lock:
+        return _recent_test_tracks.pop(key, set())
+
+
+def _attempt_track(path_str: str, task_id: str, session_id: str) -> None:
+    """Best-effort auto-track. Never raises."""
+    try:
+        p = Path(path_str).expanduser()
+    except Exception:
+        return
+    if not p.exists():
+        return
+    category = dg.guess_category(p)
+    if category is None:
+        return
+    newly = dg.track(str(p), category, silent=True)
+    if newly:
+        _record_track(task_id, session_id, p, category)
+
+
+def _extract_paths_from_write_file(args: Dict[str, Any]) -> Set[str]:
+    path = args.get(_WRITE_FILE_PATH_KEY)
+    return {path} if isinstance(path, str) and path else set()
+
+
+def _extract_paths_from_patch(args: Dict[str, Any]) -> Set[str]:
+    # The patch tool creates new files via the `mode="patch"` path too, but
+    # most of its use is editing existing files — we only care about new
+    # ephemeral creations, so treat patch conservatively and only pick up
+    # the single-file `path` arg.  Track-then-cleanup is idempotent, so
+    # re-tracking an already-tracked file is a no-op (dedup in track()).
+    path = args.get("path")
+    return {path} if isinstance(path, str) and path else set()
+
+
+def _extract_paths_from_terminal(args: Dict[str, Any], result: str) -> Set[str]:
+    """Best-effort: pull candidate filesystem paths from a terminal command
+    and its output, then let ``guess_category`` / ``is_safe_path`` filter.
+    """
+    paths: Set[str] = set()
+    cmd = args.get("command") or ""
+    if isinstance(cmd, str) and cmd:
+        # Tokenise the command — catches `touch /tmp/hermes-x/test_foo.py`
+        try:
+            for tok in shlex.split(cmd, posix=True):
+                if tok.startswith(("/", "~")):
+                    paths.add(tok)
+        except ValueError:
+            pass
+    # Only scan the result text if it's a reasonable size (avoid 50KB dumps).
+    if isinstance(result, str) and len(result) < 4096:
+        for match in _TERMINAL_PATH_REGEX.findall(result):
+            paths.add(match)
+    return paths
+
+
+# ---------------------------------------------------------------------------
+# Hooks
+# ---------------------------------------------------------------------------
+
+def _on_post_tool_call(
+    tool_name: str = "",
+    args: Optional[Dict[str, Any]] = None,
+    result: Any = None,
+    task_id: str = "",
+    session_id: str = "",
+    tool_call_id: str = "",
+    **_: Any,
+) -> None:
+    """Auto-track ephemeral files created by recent tool calls."""
+    if not isinstance(args, dict):
+        return
+
+    candidates: Set[str] = set()
+    if tool_name == "write_file":
+        candidates = _extract_paths_from_write_file(args)
+    elif tool_name == "patch":
+        candidates = _extract_paths_from_patch(args)
+    elif tool_name == "terminal":
+        candidates = _extract_paths_from_terminal(args, result if isinstance(result, str) else "")
+    else:
+        return
+
+    for path_str in candidates:
+        _attempt_track(path_str, task_id, session_id)
+
+
+def _on_session_end(
+    session_id: str = "",
+    completed: bool = True,
+    interrupted: bool = False,
+    **_: Any,
+) -> None:
+    """Run quick cleanup if any test files were tracked during this turn."""
+    # Drain both task-level and session-level buckets.  In practice only one
+    # is populated per turn; the other is empty.
+    drained_session = _drain("", session_id)
+    # Also drain any task-scoped buckets that happen to exist.  This is a
+    # cheap sweep: if an agent spawned subagents (each with their own
+    # task_id) they'll have recorded into separate buckets; we want to
+    # cleanup them all at session end.
+    with _lock:
+        task_buckets = list(_recent_test_tracks.keys())
+    for key in task_buckets:
+        if key and key != session_id:
+            _recent_test_tracks.pop(key, None)
+
+    if not drained_session and not task_buckets:
+        return
+
+    try:
+        summary = dg.quick()
+    except Exception as exc:
+        logger.debug("disk-cleanup quick cleanup failed: %s", exc)
+        return
+
+    if summary["deleted"] or summary["empty_dirs"]:
+        dg._log(
+            f"AUTO_QUICK (session_end): deleted={summary['deleted']} "
+            f"dirs={summary['empty_dirs']} freed={dg.fmt_size(summary['freed'])}"
+        )
+
+
+# ---------------------------------------------------------------------------
+# Slash command
+# ---------------------------------------------------------------------------
+
+_HELP_TEXT = """\
+/disk-cleanup — ephemeral-file cleanup
+
+Subcommands:
+  status                     Per-category breakdown + top-10 largest
+  dry-run                    Preview what quick/deep would delete
+  quick                      Run safe cleanup now (no prompts)
+  deep                       Run quick, then list items that need prompts
+  track <path> <category>    Manually add a path to tracking
+  forget <path>              Stop tracking a path (does not delete)
+
+Categories: temp | test | research | download | chrome-profile | cron-output | other
+
+All operations are scoped to HERMES_HOME and /tmp/hermes-*.
+Test files are auto-tracked on write_file / terminal and auto-cleaned at session end.
+"""
+
+
+def _fmt_summary(summary: Dict[str, Any]) -> str:
+    base = (
+        f"[disk-cleanup] Cleaned {summary['deleted']} files + "
+        f"{summary['empty_dirs']} empty dirs, freed {dg.fmt_size(summary['freed'])}."
+    )
+    if summary.get("errors"):
+        base += f"\n  {len(summary['errors'])} error(s); see cleanup.log."
+    return base
+
+
+def _handle_slash(raw_args: str) -> Optional[str]:
+    argv = raw_args.strip().split()
+    if not argv or argv[0] in ("help", "-h", "--help"):
+        return _HELP_TEXT
+
+    sub = argv[0]
+
+    if sub == "status":
+        return dg.format_status(dg.status())
+
+    if sub == "dry-run":
+        auto, prompt = dg.dry_run()
+        auto_size = sum(i["size"] for i in auto)
+        prompt_size = sum(i["size"] for i in prompt)
+        lines = [
+            "Dry-run preview (nothing deleted):",
+            f"  Auto-delete : {len(auto)} files ({dg.fmt_size(auto_size)})",
+        ]
+        for item in auto:
+            lines.append(f"    [{item['category']}] {item['path']}")
+        lines.append(
+            f"  Needs prompt: {len(prompt)} files ({dg.fmt_size(prompt_size)})"
+        )
+        for item in prompt:
+            lines.append(f"    [{item['category']}] {item['path']}")
+        lines.append(
+            f"\n  Total potential: {dg.fmt_size(auto_size + prompt_size)}"
+        )
+        return "\n".join(lines)
+
+    if sub == "quick":
+        return _fmt_summary(dg.quick())
+
+    if sub == "deep":
+        # In-session deep can't prompt the user interactively — show what
+        # quick cleaned plus the items that WOULD need confirmation.
+        quick_summary = dg.quick()
+        _auto, prompt_items = dg.dry_run()
+        lines = [_fmt_summary(quick_summary)]
+        if prompt_items:
+            size = sum(i["size"] for i in prompt_items)
+            lines.append(
+                f"\n{len(prompt_items)} item(s) need confirmation "
+                f"({dg.fmt_size(size)}):"
+            )
+            for item in prompt_items:
+                lines.append(f"  [{item['category']}] {item['path']}")
+            lines.append(
+                "\nRun `/disk-cleanup forget <path>` to skip, or delete "
+                "manually via terminal."
+            )
+        return "\n".join(lines)
+
+    if sub == "track":
+        if len(argv) < 3:
+            return "Usage: /disk-cleanup track <path> <category>"
+        path_arg = argv[1]
+        category = argv[2]
+        if category not in dg.ALLOWED_CATEGORIES:
+            return (
+                f"Unknown category '{category}'. "
+                f"Allowed: {sorted(dg.ALLOWED_CATEGORIES)}"
+            )
+        if dg.track(path_arg, category, silent=True):
+            return f"Tracked {path_arg} as '{category}'."
+        return (
+            f"Not tracked (already present, missing, or outside HERMES_HOME): "
+            f"{path_arg}"
+        )
+
+    if sub == "forget":
+        if len(argv) < 2:
+            return "Usage: /disk-cleanup forget <path>"
+        n = dg.forget(argv[1])
+        return (
+            f"Removed {n} tracking entr{'y' if n == 1 else 'ies'} for {argv[1]}."
+            if n else f"Not found in tracking: {argv[1]}"
+        )
+
+    return f"Unknown subcommand: {sub}\n\n{_HELP_TEXT}"
+
+
+# ---------------------------------------------------------------------------
+# Plugin registration
+# ---------------------------------------------------------------------------
+
+def register(ctx) -> None:
+    ctx.register_hook("post_tool_call", _on_post_tool_call)
+    ctx.register_hook("on_session_end", _on_session_end)
+    ctx.register_command(
+        "disk-cleanup",
+        handler=_handle_slash,
+        description="Track and clean up ephemeral Hermes session files.",
+    )

plugins/disk-cleanup/disk_cleanup.py

@@ -0,0 +1,496 @@
+"""disk_cleanup — ephemeral file cleanup for Hermes Agent.
+
+Library module wrapping the deterministic cleanup rules written by
+@LVT382009 in PR #12212. The plugin ``__init__.py`` wires these
+functions into ``post_tool_call`` and ``on_session_end`` hooks so
+tracking and cleanup happen automatically — the agent never needs to
+call a tool or remember a skill.
+
+Rules:
+  - test files    → delete immediately at task end (age >= 0)
+  - temp files    → delete after 7 days
+  - cron-output   → delete after 14 days
+  - empty dirs    → always delete (under HERMES_HOME)
+  - research      → keep 10 newest, prompt for older (deep only)
+  - chrome-profile→ prompt after 14 days (deep only)
+  - >500 MB files → prompt always (deep only)
+
+Scope: strictly HERMES_HOME and /tmp/hermes-*
+Never touches: ~/.hermes/logs/ or any system directory.
+"""
+
+from __future__ import annotations
+
+import json
+import logging
+import shutil
+from datetime import datetime, timezone
+from pathlib import Path
+from typing import Any, Dict, List, Optional, Tuple
+
+try:
+    from hermes_constants import get_hermes_home
+except Exception:  # pragma: no cover — plugin may load before constants resolves
+    import os
+
+    def get_hermes_home() -> Path:  # type: ignore[no-redef]
+        val = (os.environ.get("HERMES_HOME") or "").strip()
+        return Path(val).resolve() if val else (Path.home() / ".hermes").resolve()
+
+
+logger = logging.getLogger(__name__)
+
+
+# ---------------------------------------------------------------------------
+# Paths
+# ---------------------------------------------------------------------------
+
+def get_state_dir() -> Path:
+    """State dir — separate from ``$HERMES_HOME/logs/``."""
+    return get_hermes_home() / "disk-cleanup"
+
+
+def get_tracked_file() -> Path:
+    return get_state_dir() / "tracked.json"
+
+
+def get_log_file() -> Path:
+    """Audit log — intentionally NOT under ``$HERMES_HOME/logs/``."""
+    return get_state_dir() / "cleanup.log"
+
+
+# ---------------------------------------------------------------------------
+# Path safety
+# ---------------------------------------------------------------------------
+
+def is_safe_path(path: Path) -> bool:
+    """Accept only paths under HERMES_HOME or ``/tmp/hermes-*``.
+
+    Rejects Windows mounts (``/mnt/c`` etc.) and any system directory.
+    """
+    hermes_home = get_hermes_home()
+    try:
+        path.resolve().relative_to(hermes_home)
+        return True
+    except (ValueError, OSError):
+        pass
+    # Allow /tmp/hermes-* explicitly
+    parts = path.parts
+    if len(parts) >= 3 and parts[1] == "tmp" and parts[2].startswith("hermes-"):
+        return True
+    return False
+
+
+# ---------------------------------------------------------------------------
+# Audit log
+# ---------------------------------------------------------------------------
+
+def _log(message: str) -> None:
+    try:
+        log_file = get_log_file()
+        log_file.parent.mkdir(parents=True, exist_ok=True)
+        ts = datetime.now(timezone.utc).strftime("%Y-%m-%d %H:%M:%S")
+        with open(log_file, "a") as f:
+            f.write(f"[{ts}] {message}\n")
+    except OSError:
+        # Never let the audit log break the agent loop.
+        pass
+
+
+# ---------------------------------------------------------------------------
+# tracked.json — atomic read/write, backup scoped to tracked.json only
+# ---------------------------------------------------------------------------
+
+def load_tracked() -> List[Dict[str, Any]]:
+    """Load tracked.json.  Restores from ``.bak`` on corruption."""
+    tf = get_tracked_file()
+    tf.parent.mkdir(parents=True, exist_ok=True)
+
+    if not tf.exists():
+        return []
+
+    try:
+        return json.loads(tf.read_text())
+    except (json.JSONDecodeError, ValueError):
+        bak = tf.with_suffix(".json.bak")
+        if bak.exists():
+            try:
+                data = json.loads(bak.read_text())
+                _log("WARN: tracked.json corrupted — restored from .bak")
+                return data
+            except Exception:
+                pass
+        _log("WARN: tracked.json corrupted, no backup — starting fresh")
+        return []
+
+
+def save_tracked(tracked: List[Dict[str, Any]]) -> None:
+    """Atomic write: ``.tmp`` → backup old → rename."""
+    tf = get_tracked_file()
+    tf.parent.mkdir(parents=True, exist_ok=True)
+    tmp = tf.with_suffix(".json.tmp")
+    tmp.write_text(json.dumps(tracked, indent=2))
+    if tf.exists():
+        shutil.copy2(tf, tf.with_suffix(".json.bak"))
+    tmp.replace(tf)
+
+
+# ---------------------------------------------------------------------------
+# Categories
+# ---------------------------------------------------------------------------
+
+ALLOWED_CATEGORIES = {
+    "temp", "test", "research", "download",
+    "chrome-profile", "cron-output", "other",
+}
+
+
+def fmt_size(n: float) -> str:
+    for unit in ("B", "KB", "MB", "GB", "TB"):
+        if n < 1024:
+            return f"{n:.1f} {unit}"
+        n /= 1024
+    return f"{n:.1f} PB"
+
+
+# ---------------------------------------------------------------------------
+# Track / forget
+# ---------------------------------------------------------------------------
+
+def track(path_str: str, category: str, silent: bool = False) -> bool:
+    """Register a file for tracking. Returns True if newly tracked."""
+    if category not in ALLOWED_CATEGORIES:
+        _log(f"WARN: unknown category '{category}', using 'other'")
+        category = "other"
+
+    path = Path(path_str).resolve()
+
+    if not path.exists():
+        _log(f"SKIP: {path} (does not exist)")
+        return False
+
+    if not is_safe_path(path):
+        _log(f"REJECT: {path} (outside HERMES_HOME)")
+        return False
+
+    size = path.stat().st_size if path.is_file() else 0
+    tracked = load_tracked()
+
+    # Deduplicate
+    if any(item["path"] == str(path) for item in tracked):
+        return False
+
+    tracked.append({
+        "path": str(path),
+        "timestamp": datetime.now(timezone.utc).isoformat(),
+        "category": category,
+        "size": size,
+    })
+    save_tracked(tracked)
+    _log(f"TRACKED: {path} ({category}, {fmt_size(size)})")
+    if not silent:
+        print(f"Tracked: {path} ({category}, {fmt_size(size)})")
+    return True
+
+
+def forget(path_str: str) -> int:
+    """Remove a path from tracking without deleting the file."""
+    p = Path(path_str).resolve()
+    tracked = load_tracked()
+    before = len(tracked)
+    tracked = [i for i in tracked if Path(i["path"]).resolve() != p]
+    removed = before - len(tracked)
+    if removed:
+        save_tracked(tracked)
+        _log(f"FORGOT: {p} ({removed} entries)")
+    return removed
+
+
+# ---------------------------------------------------------------------------
+# Dry run
+# ---------------------------------------------------------------------------
+
+def dry_run() -> Tuple[List[Dict], List[Dict]]:
+    """Return (auto_delete_list, needs_prompt_list) without touching files."""
+    tracked = load_tracked()
+    now = datetime.now(timezone.utc)
+
+    auto: List[Dict] = []
+    prompt: List[Dict] = []
+
+    for item in tracked:
+        p = Path(item["path"])
+        if not p.exists():
+            continue
+        age = (now - datetime.fromisoformat(item["timestamp"])).days
+        cat = item["category"]
+        size = item["size"]
+
+        if cat == "test":
+            auto.append(item)
+        elif cat == "temp" and age > 7:
+            auto.append(item)
+        elif cat == "cron-output" and age > 14:
+            auto.append(item)
+        elif cat == "research" and age > 30:
+            prompt.append(item)
+        elif cat == "chrome-profile" and age > 14:
+            prompt.append(item)
+        elif size > 500 * 1024 * 1024:
+            prompt.append(item)
+
+    return auto, prompt
+
+
+# ---------------------------------------------------------------------------
+# Quick cleanup
+# ---------------------------------------------------------------------------
+
+def quick() -> Dict[str, Any]:
+    """Safe deterministic cleanup — no prompts.
+
+    Returns: ``{"deleted": N, "empty_dirs": N, "freed": bytes,
+               "errors": [str, ...]}``.
+    """
+    tracked = load_tracked()
+    now = datetime.now(timezone.utc)
+    deleted = 0
+    freed = 0
+    new_tracked: List[Dict] = []
+    errors: List[str] = []
+
+    for item in tracked:
+        p = Path(item["path"])
+        cat = item["category"]
+
+        if not p.exists():
+            _log(f"STALE: {p} (removed from tracking)")
+            continue
+
+        age = (now - datetime.fromisoformat(item["timestamp"])).days
+
+        should_delete = (
+            cat == "test"
+            or (cat == "temp" and age > 7)
+            or (cat == "cron-output" and age > 14)
+        )
+
+        if should_delete:
+            try:
+                if p.is_file():
+                    p.unlink()
+                elif p.is_dir():
+                    shutil.rmtree(p)
+                freed += item["size"]
+                deleted += 1
+                _log(f"DELETED: {p} ({cat}, {fmt_size(item['size'])})")
+            except OSError as e:
+                _log(f"ERROR deleting {p}: {e}")
+                errors.append(f"{p}: {e}")
+                new_tracked.append(item)
+        else:
+            new_tracked.append(item)
+
+    # Remove empty dirs under HERMES_HOME (but leave HERMES_HOME itself and
+    # a short list of well-known top-level state dirs alone — a fresh install
+    # has these empty, and deleting them would surprise the user).
+    hermes_home = get_hermes_home()
+    _PROTECTED_TOP_LEVEL = {
+        "logs", "memories", "sessions", "cron", "cronjobs",
+        "cache", "skills", "plugins", "disk-cleanup", "optional-skills",
+        "hermes-agent", "backups", "profiles", ".worktrees",
+    }
+    empty_removed = 0
+    try:
+        for dirpath in sorted(hermes_home.rglob("*"), reverse=True):
+            if not dirpath.is_dir() or dirpath == hermes_home:
+                continue
+            try:
+                rel_parts = dirpath.relative_to(hermes_home).parts
+            except ValueError:
+                continue
+            # Skip the well-known top-level state dirs themselves.
+            if len(rel_parts) == 1 and rel_parts[0] in _PROTECTED_TOP_LEVEL:
+                continue
+            try:
+                if not any(dirpath.iterdir()):
+                    dirpath.rmdir()
+                    empty_removed += 1
+                    _log(f"DELETED: {dirpath} (empty dir)")
+            except OSError:
+                pass
+    except OSError:
+        pass
+
+    save_tracked(new_tracked)
+    _log(
+        f"QUICK_SUMMARY: {deleted} files, {empty_removed} dirs, "
+        f"{fmt_size(freed)}"
+    )
+    return {
+        "deleted": deleted,
+        "empty_dirs": empty_removed,
+        "freed": freed,
+        "errors": errors,
+    }
+
+
+# ---------------------------------------------------------------------------
+# Deep cleanup (interactive — not called from plugin hooks)
+# ---------------------------------------------------------------------------
+
+def deep(
+    confirm: Optional[callable] = None,
+) -> Dict[str, Any]:
+    """Deep cleanup.
+
+    Runs :func:`quick` first, then asks the *confirm* callable for each
+    risky item (research > 30d beyond 10 newest, chrome-profile > 14d,
+    any file > 500 MB).  *confirm(item)* must return True to delete.
+
+    Returns: ``{"quick": {...}, "deep_deleted": N, "deep_freed": bytes}``.
+    """
+    quick_result = quick()
+
+    if confirm is None:
+        # No interactive confirmer — deep stops after the quick pass.
+        return {"quick": quick_result, "deep_deleted": 0, "deep_freed": 0}
+
+    tracked = load_tracked()
+    now = datetime.now(timezone.utc)
+    research, chrome, large = [], [], []
+
+    for item in tracked:
+        p = Path(item["path"])
+        if not p.exists():
+            continue
+        age = (now - datetime.fromisoformat(item["timestamp"])).days
+        cat = item["category"]
+
+        if cat == "research" and age > 30:
+            research.append(item)
+        elif cat == "chrome-profile" and age > 14:
+            chrome.append(item)
+        elif item["size"] > 500 * 1024 * 1024:
+            large.append(item)
+
+    research.sort(key=lambda x: x["timestamp"], reverse=True)
+    old_research = research[10:]
+
+    freed, count = 0, 0
+    to_remove: List[Dict] = []
+
+    for group in (old_research, chrome, large):
+        for item in group:
+            if confirm(item):
+                try:
+                    p = Path(item["path"])
+                    if p.is_file():
+                        p.unlink()
+                    elif p.is_dir():
+                        shutil.rmtree(p)
+                    to_remove.append(item)
+                    freed += item["size"]
+                    count += 1
+                    _log(
+                        f"DELETED: {p} ({item['category']}, "
+                        f"{fmt_size(item['size'])})"
+                    )
+                except OSError as e:
+                    _log(f"ERROR deleting {item['path']}: {e}")
+
+    if to_remove:
+        remove_paths = {i["path"] for i in to_remove}
+        save_tracked([i for i in tracked if i["path"] not in remove_paths])
+
+    return {"quick": quick_result, "deep_deleted": count, "deep_freed": freed}
+
+
+# ---------------------------------------------------------------------------
+# Status
+# ---------------------------------------------------------------------------
+
+def status() -> Dict[str, Any]:
+    """Return per-category breakdown and top 10 largest tracked files."""
+    tracked = load_tracked()
+    cats: Dict[str, Dict] = {}
+    for item in tracked:
+        c = item["category"]
+        cats.setdefault(c, {"count": 0, "size": 0})
+        cats[c]["count"] += 1
+        cats[c]["size"] += item["size"]
+
+    existing = [
+        (i["path"], i["size"], i["category"])
+        for i in tracked if Path(i["path"]).exists()
+    ]
+    existing.sort(key=lambda x: x[1], reverse=True)
+
+    return {
+        "categories": cats,
+        "top10": existing[:10],
+        "total_tracked": len(tracked),
+    }
+
+
+def format_status(s: Dict[str, Any]) -> str:
+    """Human-readable status string (for slash command output)."""
+    lines = [f"{'Category':<20} {'Files':>6}  {'Size':>10}", "-" * 40]
+    cats = s["categories"]
+    for cat, d in sorted(cats.items(), key=lambda x: x[1]["size"], reverse=True):
+        lines.append(f"{cat:<20} {d['count']:>6}  {fmt_size(d['size']):>10}")
+
+    if not cats:
+        lines.append("(nothing tracked yet)")
+
+    lines.append("")
+    lines.append("Top 10 largest tracked files:")
+    if not s["top10"]:
+        lines.append("  (none)")
+    else:
+        for rank, (path, size, cat) in enumerate(s["top10"], 1):
+            lines.append(f"  {rank:>2}. {fmt_size(size):>8}  [{cat}]  {path}")
+    return "\n".join(lines)
+
+
+# ---------------------------------------------------------------------------
+# Auto-categorisation from tool-call inspection
+# ---------------------------------------------------------------------------
+
+_TEST_PATTERNS = ("test_", "tmp_")
+_TEST_SUFFIXES = (".test.py", ".test.js", ".test.ts", ".test.md")
+
+
+def guess_category(path: Path) -> Optional[str]:
+    """Return a category label for *path*, or None if we shouldn't track it.
+
+    Used by the ``post_tool_call`` hook to auto-track ephemeral files.
+    """
+    if not is_safe_path(path):
+        return None
+
+    # Skip the state dir itself, logs, memory files, sessions, config.
+    hermes_home = get_hermes_home()
+    try:
+        rel = path.resolve().relative_to(hermes_home)
+        top = rel.parts[0] if rel.parts else ""
+        if top in {
+            "disk-cleanup", "logs", "memories", "sessions", "config.yaml",
+            "skills", "plugins", ".env", "USER.md", "MEMORY.md", "SOUL.md",
+            "auth.json", "hermes-agent",
+        }:
+            return None
+        if top == "cron" or top == "cronjobs":
+            return "cron-output"
+        if top == "cache":
+            return "temp"
+    except ValueError:
+        # Path isn't under HERMES_HOME (e.g. /tmp/hermes-*) — fall through.
+        pass
+
+    name = path.name
+    if name.startswith(_TEST_PATTERNS):
+        return "test"
+    if any(name.endswith(sfx) for sfx in _TEST_SUFFIXES):
+        return "test"
+    return None

plugins/disk-cleanup/plugin.yaml

@@ -0,0 +1,7 @@
+name: disk-cleanup
+version: 2.0.0
+description: "Auto-track and clean up ephemeral files (test scripts, temp outputs, cron logs) created during Hermes sessions. Runs via plugin hooks — no agent action required."
+author: "@LVT382009 (original), NousResearch (plugin port)"
+hooks:
+  - post_tool_call
+  - on_session_end

plugins/image_gen/openai-codex/__init__.py

@@ -0,0 +1,378 @@
+"""OpenAI image generation backend — ChatGPT/Codex OAuth variant.
+
+Identical model catalog and tier semantics to the ``openai`` image-gen plugin
+(``gpt-image-2`` at low/medium/high quality), but routes the request through
+the Codex Responses API ``image_generation`` tool instead of the
+``images.generate`` REST endpoint. This lets users who are already
+authenticated with Codex/ChatGPT generate images without configuring a
+separate ``OPENAI_API_KEY``.
+
+Selection precedence for the tier (first hit wins):
+
+1. ``OPENAI_IMAGE_MODEL`` env var (escape hatch for scripts / tests)
+2. ``image_gen.openai-codex.model`` in ``config.yaml``
+3. ``image_gen.model`` in ``config.yaml`` (when it's one of our tier IDs)
+4. :data:`DEFAULT_MODEL` — ``gpt-image-2-medium``
+
+Output is saved as PNG under ``$HERMES_HOME/cache/images/``.
+"""
+
+from __future__ import annotations
+
+import logging
+from typing import Any, Dict, List, Optional, Tuple
+
+from agent.image_gen_provider import (
+    DEFAULT_ASPECT_RATIO,
+    ImageGenProvider,
+    error_response,
+    resolve_aspect_ratio,
+    save_b64_image,
+    success_response,
+)
+
+logger = logging.getLogger(__name__)
+
+
+# ---------------------------------------------------------------------------
+# Model catalog — mirrors the ``openai`` plugin so the picker UX is identical.
+# ---------------------------------------------------------------------------
+
+API_MODEL = "gpt-image-2"
+
+_MODELS: Dict[str, Dict[str, Any]] = {
+    "gpt-image-2-low": {
+        "display": "GPT Image 2 (Low)",
+        "speed": "~15s",
+        "strengths": "Fast iteration, lowest cost",
+        "quality": "low",
+    },
+    "gpt-image-2-medium": {
+        "display": "GPT Image 2 (Medium)",
+        "speed": "~40s",
+        "strengths": "Balanced — default",
+        "quality": "medium",
+    },
+    "gpt-image-2-high": {
+        "display": "GPT Image 2 (High)",
+        "speed": "~2min",
+        "strengths": "Highest fidelity, strongest prompt adherence",
+        "quality": "high",
+    },
+}
+
+DEFAULT_MODEL = "gpt-image-2-medium"
+
+_SIZES = {
+    "landscape": "1536x1024",
+    "square": "1024x1024",
+    "portrait": "1024x1536",
+}
+
+# Codex Responses surface used for the request. The chat model itself is only
+# the host that calls the ``image_generation`` tool; the actual image work is
+# done by ``API_MODEL``.
+_CODEX_CHAT_MODEL = "gpt-5.4"
+_CODEX_BASE_URL = "https://chatgpt.com/backend-api/codex"
+_CODEX_INSTRUCTIONS = (
+    "You are an assistant that must fulfill image generation requests by "
+    "using the image_generation tool when provided."
+)
+
+
+# ---------------------------------------------------------------------------
+# Config + auth helpers
+# ---------------------------------------------------------------------------
+
+
+def _load_image_gen_config() -> Dict[str, Any]:
+    """Read ``image_gen`` from config.yaml (returns {} on any failure)."""
+    try:
+        from hermes_cli.config import load_config
+
+        cfg = load_config()
+        section = cfg.get("image_gen") if isinstance(cfg, dict) else None
+        return section if isinstance(section, dict) else {}
+    except Exception as exc:
+        logger.debug("Could not load image_gen config: %s", exc)
+        return {}
+
+
+def _resolve_model() -> Tuple[str, Dict[str, Any]]:
+    """Decide which tier to use and return ``(model_id, meta)``."""
+    import os
+
+    env_override = os.environ.get("OPENAI_IMAGE_MODEL")
+    if env_override and env_override in _MODELS:
+        return env_override, _MODELS[env_override]
+
+    cfg = _load_image_gen_config()
+    sub = cfg.get("openai-codex") if isinstance(cfg.get("openai-codex"), dict) else {}
+    candidate: Optional[str] = None
+    if isinstance(sub, dict):
+        value = sub.get("model")
+        if isinstance(value, str) and value in _MODELS:
+            candidate = value
+    if candidate is None:
+        top = cfg.get("model")
+        if isinstance(top, str) and top in _MODELS:
+            candidate = top
+
+    if candidate is not None:
+        return candidate, _MODELS[candidate]
+
+    return DEFAULT_MODEL, _MODELS[DEFAULT_MODEL]
+
+
+def _read_codex_access_token() -> Optional[str]:
+    """Return a usable Codex OAuth token, or None.
+
+    Delegates to the canonical reader in ``agent.auxiliary_client`` so token
+    expiry, credential pool selection, and JWT decoding stay in one place.
+    """
+    try:
+        from agent.auxiliary_client import _read_codex_access_token as _reader
+
+        token = _reader()
+        if isinstance(token, str) and token.strip():
+            return token.strip()
+        return None
+    except Exception as exc:
+        logger.debug("Could not resolve Codex access token: %s", exc)
+        return None
+
+
+def _build_codex_client():
+    """Return an OpenAI client pointed at the ChatGPT/Codex backend, or None."""
+    token = _read_codex_access_token()
+    if not token:
+        return None
+    try:
+        import openai
+        from agent.auxiliary_client import _codex_cloudflare_headers
+
+        return openai.OpenAI(
+            api_key=token,
+            base_url=_CODEX_BASE_URL,
+            default_headers=_codex_cloudflare_headers(token),
+        )
+    except Exception as exc:
+        logger.debug("Could not build Codex image client: %s", exc)
+        return None
+
+
+def _collect_image_b64(client: Any, *, prompt: str, size: str, quality: str) -> Optional[str]:
+    """Stream a Codex Responses image_generation call and return the b64 image."""
+    image_b64: Optional[str] = None
+
+    with client.responses.stream(
+        model=_CODEX_CHAT_MODEL,
+        store=False,
+        instructions=_CODEX_INSTRUCTIONS,
+        input=[{
+            "type": "message",
+            "role": "user",
+            "content": [{"type": "input_text", "text": prompt}],
+        }],
+        tools=[{
+            "type": "image_generation",
+            "model": API_MODEL,
+            "size": size,
+            "quality": quality,
+            "output_format": "png",
+            "background": "opaque",
+            "partial_images": 1,
+        }],
+        tool_choice={
+            "type": "allowed_tools",
+            "mode": "required",
+            "tools": [{"type": "image_generation"}],
+        },
+    ) as stream:
+        for event in stream:
+            event_type = getattr(event, "type", "")
+            if event_type == "response.output_item.done":
+                item = getattr(event, "item", None)
+                if getattr(item, "type", None) == "image_generation_call":
+                    result = getattr(item, "result", None)
+                    if isinstance(result, str) and result:
+                        image_b64 = result
+            elif event_type == "response.image_generation_call.partial_image":
+                partial = getattr(event, "partial_image_b64", None)
+                if isinstance(partial, str) and partial:
+                    image_b64 = partial
+        final = stream.get_final_response()
+
+    # Final-response sweep covers the case where the stream finished before
+    # we observed the ``output_item.done`` event for the image call.
+    for item in getattr(final, "output", None) or []:
+        if getattr(item, "type", None) == "image_generation_call":
+            result = getattr(item, "result", None)
+            if isinstance(result, str) and result:
+                image_b64 = result
+
+    return image_b64
+
+
+# ---------------------------------------------------------------------------
+# Provider
+# ---------------------------------------------------------------------------
+
+
+class OpenAICodexImageGenProvider(ImageGenProvider):
+    """gpt-image-2 routed through ChatGPT/Codex OAuth instead of an API key."""
+
+    @property
+    def name(self) -> str:
+        return "openai-codex"
+
+    @property
+    def display_name(self) -> str:
+        return "OpenAI (Codex auth)"
+
+    def is_available(self) -> bool:
+        if not _read_codex_access_token():
+            return False
+        try:
+            import openai  # noqa: F401
+        except ImportError:
+            return False
+        return True
+
+    def list_models(self) -> List[Dict[str, Any]]:
+        return [
+            {
+                "id": model_id,
+                "display": meta["display"],
+                "speed": meta["speed"],
+                "strengths": meta["strengths"],
+                "price": "varies",
+            }
+            for model_id, meta in _MODELS.items()
+        ]
+
+    def default_model(self) -> Optional[str]:
+        return DEFAULT_MODEL
+
+    def get_setup_schema(self) -> Dict[str, Any]:
+        return {
+            "name": "OpenAI (Codex auth)",
+            "badge": "free",
+            "tag": "gpt-image-2 via ChatGPT/Codex OAuth — no API key required",
+            "env_vars": [],
+            "post_setup_hint": (
+                "Sign in with `hermes auth codex` (or `hermes setup` → Codex) "
+                "if you haven't already. No API key needed."
+            ),
+        }
+
+    def generate(
+        self,
+        prompt: str,
+        aspect_ratio: str = DEFAULT_ASPECT_RATIO,
+        **kwargs: Any,
+    ) -> Dict[str, Any]:
+        prompt = (prompt or "").strip()
+        aspect = resolve_aspect_ratio(aspect_ratio)
+
+        if not prompt:
+            return error_response(
+                error="Prompt is required and must be a non-empty string",
+                error_type="invalid_argument",
+                provider="openai-codex",
+                aspect_ratio=aspect,
+            )
+
+        if not _read_codex_access_token():
+            return error_response(
+                error=(
+                    "No Codex/ChatGPT OAuth credentials available. Run "
+                    "`hermes auth codex` (or `hermes setup` → Codex) to sign in."
+                ),
+                error_type="auth_required",
+                provider="openai-codex",
+                aspect_ratio=aspect,
+            )
+
+        try:
+            import openai  # noqa: F401
+        except ImportError:
+            return error_response(
+                error="openai Python package not installed (pip install openai)",
+                error_type="missing_dependency",
+                provider="openai-codex",
+                aspect_ratio=aspect,
+            )
+
+        tier_id, meta = _resolve_model()
+        size = _SIZES.get(aspect, _SIZES["square"])
+
+        client = _build_codex_client()
+        if client is None:
+            return error_response(
+                error="Could not initialize Codex image client",
+                error_type="auth_required",
+                provider="openai-codex",
+                model=tier_id,
+                prompt=prompt,
+                aspect_ratio=aspect,
+            )
+
+        try:
+            b64 = _collect_image_b64(
+                client,
+                prompt=prompt,
+                size=size,
+                quality=meta["quality"],
+            )
+        except Exception as exc:
+            logger.debug("Codex image generation failed", exc_info=True)
+            return error_response(
+                error=f"OpenAI image generation via Codex auth failed: {exc}",
+                error_type="api_error",
+                provider="openai-codex",
+                model=tier_id,
+                prompt=prompt,
+                aspect_ratio=aspect,
+            )
+
+        if not b64:
+            return error_response(
+                error="Codex response contained no image_generation_call result",
+                error_type="empty_response",
+                provider="openai-codex",
+                model=tier_id,
+                prompt=prompt,
+                aspect_ratio=aspect,
+            )
+
+        try:
+            saved_path = save_b64_image(b64, prefix=f"openai_codex_{tier_id}")
+        except Exception as exc:
+            return error_response(
+                error=f"Could not save image to cache: {exc}",
+                error_type="io_error",
+                provider="openai-codex",
+                model=tier_id,
+                prompt=prompt,
+                aspect_ratio=aspect,
+            )
+
+        return success_response(
+            image=str(saved_path),
+            model=tier_id,
+            prompt=prompt,
+            aspect_ratio=aspect,
+            provider="openai-codex",
+            extra={"size": size, "quality": meta["quality"]},
+        )
+
+
+# ---------------------------------------------------------------------------
+# Plugin entry point
+# ---------------------------------------------------------------------------
+
+
+def register(ctx) -> None:
+    """Plugin entry point — register the Codex-backed image-gen provider."""
+    ctx.register_image_gen_provider(OpenAICodexImageGenProvider())

plugins/image_gen/openai-codex/plugin.yaml

@@ -0,0 +1,5 @@
+name: openai-codex
+version: 1.0.0
+description: "OpenAI image generation backed by ChatGPT/Codex OAuth (gpt-image-2 via the Responses image_generation tool). Saves generated images to $HERMES_HOME/cache/images/."
+author: NousResearch
+kind: backend

plugins/image_gen/openai/__init__.py

@@ -0,0 +1,303 @@
+"""OpenAI image generation backend.
+
+Exposes OpenAI's ``gpt-image-2`` model at three quality tiers as an
+:class:`ImageGenProvider` implementation. The tiers are implemented as
+three virtual model IDs so the ``hermes tools`` model picker and the
+``image_gen.model`` config key behave like any other multi-model backend:
+
+    gpt-image-2-low     ~15s   fastest, good for iteration
+    gpt-image-2-medium  ~40s   default — balanced
+    gpt-image-2-high    ~2min  slowest, highest fidelity
+
+All three hit the same underlying API model (``gpt-image-2``) with a
+different ``quality`` parameter. Output is base64 JSON → saved under
+``$HERMES_HOME/cache/images/``.
+
+Selection precedence (first hit wins):
+
+1. ``OPENAI_IMAGE_MODEL`` env var (escape hatch for scripts / tests)
+2. ``image_gen.openai.model`` in ``config.yaml``
+3. ``image_gen.model`` in ``config.yaml`` (when it's one of our tier IDs)
+4. :data:`DEFAULT_MODEL` — ``gpt-image-2-medium``
+"""
+
+from __future__ import annotations
+
+import logging
+import os
+from typing import Any, Dict, List, Optional, Tuple
+
+from agent.image_gen_provider import (
+    DEFAULT_ASPECT_RATIO,
+    ImageGenProvider,
+    error_response,
+    resolve_aspect_ratio,
+    save_b64_image,
+    success_response,
+)
+
+logger = logging.getLogger(__name__)
+
+
+# ---------------------------------------------------------------------------
+# Model catalog
+# ---------------------------------------------------------------------------
+#
+# All three IDs resolve to the same underlying API model with a different
+# ``quality`` setting. ``api_model`` is what gets sent to OpenAI;
+# ``quality`` is the knob that changes generation time and output fidelity.
+
+API_MODEL = "gpt-image-2"
+
+_MODELS: Dict[str, Dict[str, Any]] = {
+    "gpt-image-2-low": {
+        "display": "GPT Image 2 (Low)",
+        "speed": "~15s",
+        "strengths": "Fast iteration, lowest cost",
+        "quality": "low",
+    },
+    "gpt-image-2-medium": {
+        "display": "GPT Image 2 (Medium)",
+        "speed": "~40s",
+        "strengths": "Balanced — default",
+        "quality": "medium",
+    },
+    "gpt-image-2-high": {
+        "display": "GPT Image 2 (High)",
+        "speed": "~2min",
+        "strengths": "Highest fidelity, strongest prompt adherence",
+        "quality": "high",
+    },
+}
+
+DEFAULT_MODEL = "gpt-image-2-medium"
+
+_SIZES = {
+    "landscape": "1536x1024",
+    "square": "1024x1024",
+    "portrait": "1024x1536",
+}
+
+
+def _load_openai_config() -> Dict[str, Any]:
+    """Read ``image_gen`` from config.yaml (returns {} on any failure)."""
+    try:
+        from hermes_cli.config import load_config
+
+        cfg = load_config()
+        section = cfg.get("image_gen") if isinstance(cfg, dict) else None
+        return section if isinstance(section, dict) else {}
+    except Exception as exc:
+        logger.debug("Could not load image_gen config: %s", exc)
+        return {}
+
+
+def _resolve_model() -> Tuple[str, Dict[str, Any]]:
+    """Decide which tier to use and return ``(model_id, meta)``."""
+    env_override = os.environ.get("OPENAI_IMAGE_MODEL")
+    if env_override and env_override in _MODELS:
+        return env_override, _MODELS[env_override]
+
+    cfg = _load_openai_config()
+    openai_cfg = cfg.get("openai") if isinstance(cfg.get("openai"), dict) else {}
+    candidate: Optional[str] = None
+    if isinstance(openai_cfg, dict):
+        value = openai_cfg.get("model")
+        if isinstance(value, str) and value in _MODELS:
+            candidate = value
+    if candidate is None:
+        top = cfg.get("model")
+        if isinstance(top, str) and top in _MODELS:
+            candidate = top
+
+    if candidate is not None:
+        return candidate, _MODELS[candidate]
+
+    return DEFAULT_MODEL, _MODELS[DEFAULT_MODEL]
+
+
+# ---------------------------------------------------------------------------
+# Provider
+# ---------------------------------------------------------------------------
+
+
+class OpenAIImageGenProvider(ImageGenProvider):
+    """OpenAI ``images.generate`` backend — gpt-image-2 at low/medium/high."""
+
+    @property
+    def name(self) -> str:
+        return "openai"
+
+    @property
+    def display_name(self) -> str:
+        return "OpenAI"
+
+    def is_available(self) -> bool:
+        if not os.environ.get("OPENAI_API_KEY"):
+            return False
+        try:
+            import openai  # noqa: F401
+        except ImportError:
+            return False
+        return True
+
+    def list_models(self) -> List[Dict[str, Any]]:
+        return [
+            {
+                "id": model_id,
+                "display": meta["display"],
+                "speed": meta["speed"],
+                "strengths": meta["strengths"],
+                "price": "varies",
+            }
+            for model_id, meta in _MODELS.items()
+        ]
+
+    def default_model(self) -> Optional[str]:
+        return DEFAULT_MODEL
+
+    def get_setup_schema(self) -> Dict[str, Any]:
+        return {
+            "name": "OpenAI",
+            "badge": "paid",
+            "tag": "gpt-image-2 at low/medium/high quality tiers",
+            "env_vars": [
+                {
+                    "key": "OPENAI_API_KEY",
+                    "prompt": "OpenAI API key",
+                    "url": "https://platform.openai.com/api-keys",
+                },
+            ],
+        }
+
+    def generate(
+        self,
+        prompt: str,
+        aspect_ratio: str = DEFAULT_ASPECT_RATIO,
+        **kwargs: Any,
+    ) -> Dict[str, Any]:
+        prompt = (prompt or "").strip()
+        aspect = resolve_aspect_ratio(aspect_ratio)
+
+        if not prompt:
+            return error_response(
+                error="Prompt is required and must be a non-empty string",
+                error_type="invalid_argument",
+                provider="openai",
+                aspect_ratio=aspect,
+            )
+
+        if not os.environ.get("OPENAI_API_KEY"):
+            return error_response(
+                error=(
+                    "OPENAI_API_KEY not set. Run `hermes tools` → Image "
+                    "Generation → OpenAI to configure, or `hermes setup` "
+                    "to add the key."
+                ),
+                error_type="auth_required",
+                provider="openai",
+                aspect_ratio=aspect,
+            )
+
+        try:
+            import openai
+        except ImportError:
+            return error_response(
+                error="openai Python package not installed (pip install openai)",
+                error_type="missing_dependency",
+                provider="openai",
+                aspect_ratio=aspect,
+            )
+
+        tier_id, meta = _resolve_model()
+        size = _SIZES.get(aspect, _SIZES["square"])
+
+        # gpt-image-2 returns b64_json unconditionally and REJECTS
+        # ``response_format`` as an unknown parameter. Don't send it.
+        payload: Dict[str, Any] = {
+            "model": API_MODEL,
+            "prompt": prompt,
+            "size": size,
+            "n": 1,
+            "quality": meta["quality"],
+        }
+
+        try:
+            client = openai.OpenAI()
+            response = client.images.generate(**payload)
+        except Exception as exc:
+            logger.debug("OpenAI image generation failed", exc_info=True)
+            return error_response(
+                error=f"OpenAI image generation failed: {exc}",
+                error_type="api_error",
+                provider="openai",
+                model=tier_id,
+                prompt=prompt,
+                aspect_ratio=aspect,
+            )
+
+        data = getattr(response, "data", None) or []
+        if not data:
+            return error_response(
+                error="OpenAI returned no image data",
+                error_type="empty_response",
+                provider="openai",
+                model=tier_id,
+                prompt=prompt,
+                aspect_ratio=aspect,
+            )
+
+        first = data[0]
+        b64 = getattr(first, "b64_json", None)
+        url = getattr(first, "url", None)
+        revised_prompt = getattr(first, "revised_prompt", None)
+
+        if b64:
+            try:
+                saved_path = save_b64_image(b64, prefix=f"openai_{tier_id}")
+            except Exception as exc:
+                return error_response(
+                    error=f"Could not save image to cache: {exc}",
+                    error_type="io_error",
+                    provider="openai",
+                    model=tier_id,
+                    prompt=prompt,
+                    aspect_ratio=aspect,
+                )
+            image_ref = str(saved_path)
+        elif url:
+            # Defensive — gpt-image-2 returns b64 today, but fall back
+            # gracefully if the API ever changes.
+            image_ref = url
+        else:
+            return error_response(
+                error="OpenAI response contained neither b64_json nor URL",
+                error_type="empty_response",
+                provider="openai",
+                model=tier_id,
+                prompt=prompt,
+                aspect_ratio=aspect,
+            )
+
+        extra: Dict[str, Any] = {"size": size, "quality": meta["quality"]}
+        if revised_prompt:
+            extra["revised_prompt"] = revised_prompt
+
+        return success_response(
+            image=image_ref,
+            model=tier_id,
+            prompt=prompt,
+            aspect_ratio=aspect,
+            provider="openai",
+            extra=extra,
+        )
+
+
+# ---------------------------------------------------------------------------
+# Plugin entry point
+# ---------------------------------------------------------------------------
+
+
+def register(ctx) -> None:
+    """Plugin entry point — wire ``OpenAIImageGenProvider`` into the registry."""
+    ctx.register_image_gen_provider(OpenAIImageGenProvider())

plugins/image_gen/openai/plugin.yaml

@@ -0,0 +1,7 @@
+name: openai
+version: 1.0.0
+description: "OpenAI image generation backend (gpt-image-2). Saves generated images to $HERMES_HOME/cache/images/."
+author: NousResearch
+kind: backend
+requires_env:
+  - OPENAI_API_KEY

plugins/memory/hindsight/README.md

@@ -84,7 +84,10 @@ Config file: `~/.hermes/hindsight/config.json`
 | `retain_async` | `true` | Process retain asynchronously on the Hindsight server |
 | `retain_every_n_turns` | `1` | Retain every N turns (1 = every turn) |
 | `retain_context` | `conversation between Hermes Agent and the User` | Context label for retained memories |
-| `tags` | — | Tags applied when storing memories |
+| `retain_tags` | — | Default tags applied to retained memories; merged with per-call tool tags |
+| `retain_source` | — | Optional `metadata.source` attached to retained memories |
+| `retain_user_prefix` | `User` | Label used before user turns in auto-retained transcripts |
+| `retain_assistant_prefix` | `Assistant` | Label used before assistant turns in auto-retained transcripts |
 
 ### Integration
 
@@ -113,7 +116,7 @@ Available in `hybrid` and `tools` memory modes:
 
 | Tool | Description |
 |------|-------------|
-| `hindsight_retain` | Store information with auto entity extraction |
+| `hindsight_retain` | Store information with auto entity extraction; supports optional per-call `tags` |
 | `hindsight_recall` | Multi-strategy search (semantic + entity graph) |
 | `hindsight_reflect` | Cross-memory synthesis (LLM-powered) |
 

plugins/memory/hindsight/__init__.py

@@ -6,11 +6,15 @@ retrieval. Supports cloud (API key) and local modes.
 Original PR #1811 by benfrank241, adapted to MemoryProvider ABC.
 
 Config via environment variables:
-  HINDSIGHT_API_KEY   — API key for Hindsight Cloud
-  HINDSIGHT_BANK_ID   — memory bank identifier (default: hermes)
-  HINDSIGHT_BUDGET    — recall budget: low/mid/high (default: mid)
-  HINDSIGHT_API_URL   — API endpoint
-  HINDSIGHT_MODE      — cloud or local (default: cloud)
+  HINDSIGHT_API_KEY                — API key for Hindsight Cloud
+  HINDSIGHT_BANK_ID                — memory bank identifier (default: hermes)
+  HINDSIGHT_BUDGET                 — recall budget: low/mid/high (default: mid)
+  HINDSIGHT_API_URL                — API endpoint
+  HINDSIGHT_MODE                   — cloud or local (default: cloud)
+  HINDSIGHT_RETAIN_TAGS            — comma-separated tags attached to retained memories
+  HINDSIGHT_RETAIN_SOURCE          — metadata source value attached to retained memories
+  HINDSIGHT_RETAIN_USER_PREFIX     — label used before user turns in retained transcripts
+  HINDSIGHT_RETAIN_ASSISTANT_PREFIX — label used before assistant turns in retained transcripts
 
 Or via $HERMES_HOME/hindsight/config.json (profile-scoped), falling back to
 ~/.hindsight/config.json (legacy, shared) for backward compatibility.
@@ -24,7 +28,7 @@ import logging
 import os
 import threading
 
-from hermes_constants import get_hermes_home
+from datetime import datetime, timezone
 from typing import Any, Dict, List
 
 from agent.memory_provider import MemoryProvider
@@ -99,6 +103,11 @@ RETAIN_SCHEMA = {
         "properties": {
             "content": {"type": "string", "description": "The information to store."},
             "context": {"type": "string", "description": "Short label (e.g. 'user preference', 'project decision')."},
+            "tags": {
+                "type": "array",
+                "items": {"type": "string"},
+                "description": "Optional per-call tags to merge with configured default retain tags.",
+            },
         },
         "required": ["content"],
     },
@@ -168,6 +177,10 @@ def _load_config() -> dict:
     return {
         "mode": os.environ.get("HINDSIGHT_MODE", "cloud"),
         "apiKey": os.environ.get("HINDSIGHT_API_KEY", ""),
+        "retain_tags": os.environ.get("HINDSIGHT_RETAIN_TAGS", ""),
+        "retain_source": os.environ.get("HINDSIGHT_RETAIN_SOURCE", ""),
+        "retain_user_prefix": os.environ.get("HINDSIGHT_RETAIN_USER_PREFIX", "User"),
+        "retain_assistant_prefix": os.environ.get("HINDSIGHT_RETAIN_ASSISTANT_PREFIX", "Assistant"),
         "banks": {
             "hermes": {
                 "bankId": os.environ.get("HINDSIGHT_BANK_ID", "hermes"),
@@ -178,6 +191,48 @@ def _load_config() -> dict:
     }
 
 
+def _normalize_retain_tags(value: Any) -> List[str]:
+    """Normalize tag config/tool values to a deduplicated list of strings."""
+    if value is None:
+        return []
+
+    raw_items: list[Any]
+    if isinstance(value, list):
+        raw_items = value
+    elif isinstance(value, str):
+        text = value.strip()
+        if not text:
+            return []
+        if text.startswith("["):
+            try:
+                parsed = json.loads(text)
+            except Exception:
+                parsed = None
+            if isinstance(parsed, list):
+                raw_items = parsed
+            else:
+                raw_items = text.split(",")
+        else:
+            raw_items = text.split(",")
+    else:
+        raw_items = [value]
+
+    normalized = []
+    seen = set()
+    for item in raw_items:
+        tag = str(item).strip()
+        if not tag or tag in seen:
+            continue
+        seen.add(tag)
+        normalized.append(tag)
+    return normalized
+
+
+def _utc_timestamp() -> str:
+    """Return current UTC timestamp in ISO-8601 with milliseconds and Z suffix."""
+    return datetime.now(timezone.utc).isoformat(timespec="milliseconds").replace("+00:00", "Z")
+
+
 # ---------------------------------------------------------------------------
 # MemoryProvider implementation
 # ---------------------------------------------------------------------------
@@ -195,6 +250,19 @@ class HindsightMemoryProvider(MemoryProvider):
         self._llm_base_url = ""
         self._memory_mode = "hybrid"  # "context", "tools", or "hybrid"
         self._prefetch_method = "recall"  # "recall" or "reflect"
+        self._retain_tags: List[str] = []
+        self._retain_source = ""
+        self._retain_user_prefix = "User"
+        self._retain_assistant_prefix = "Assistant"
+        self._platform = ""
+        self._user_id = ""
+        self._user_name = ""
+        self._chat_id = ""
+        self._chat_name = ""
+        self._chat_type = ""
+        self._thread_id = ""
+        self._agent_identity = ""
+        self._turn_index = 0
         self._client = None
         self._prefetch_result = ""
         self._prefetch_lock = threading.Lock()
@@ -210,6 +278,7 @@ class HindsightMemoryProvider(MemoryProvider):
         # Retain controls
         self._auto_retain = True
         self._retain_every_n_turns = 1
+        self._retain_async = True
         self._retain_context = "conversation between Hermes Agent and the User"
         self._turn_counter = 0
         self._session_turns: list[str] = []  # accumulates ALL turns for the session
@@ -224,7 +293,6 @@ class HindsightMemoryProvider(MemoryProvider):
         # Bank
         self._bank_mission = ""
         self._bank_retain_mission: str | None = None
-        self._retain_async = True
 
     @property
     def name(self) -> str:
@@ -423,7 +491,10 @@ class HindsightMemoryProvider(MemoryProvider):
             {"key": "recall_budget", "description": "Recall thoroughness", "default": "mid", "choices": ["low", "mid", "high"]},
             {"key": "memory_mode", "description": "Memory integration mode", "default": "hybrid", "choices": ["hybrid", "context", "tools"]},
             {"key": "recall_prefetch_method", "description": "Auto-recall method", "default": "recall", "choices": ["recall", "reflect"]},
-            {"key": "tags", "description": "Tags applied when storing memories (comma-separated)", "default": ""},
+            {"key": "retain_tags", "description": "Default tags applied to retained memories (comma-separated)", "default": ""},
+            {"key": "retain_source", "description": "Metadata source value attached to retained memories", "default": ""},
+            {"key": "retain_user_prefix", "description": "Label used before user turns in retained transcripts", "default": "User"},
+            {"key": "retain_assistant_prefix", "description": "Label used before assistant turns in retained transcripts", "default": "Assistant"},
             {"key": "recall_tags", "description": "Tags to filter when searching memories (comma-separated)", "default": ""},
             {"key": "recall_tags_match", "description": "Tag matching mode for recall", "default": "any", "choices": ["any", "all", "any_strict", "all_strict"]},
             {"key": "auto_recall", "description": "Automatically recall memories before each turn", "default": True},
@@ -467,7 +538,7 @@ class HindsightMemoryProvider(MemoryProvider):
         return self._client
 
     def initialize(self, session_id: str, **kwargs) -> None:
-        self._session_id = session_id
+        self._session_id = str(session_id or "").strip()
 
         # Check client version and auto-upgrade if needed
         try:
@@ -496,6 +567,16 @@ class HindsightMemoryProvider(MemoryProvider):
             pass  # packaging not available or other issue — proceed anyway
 
         self._config = _load_config()
+        self._platform = str(kwargs.get("platform") or "").strip()
+        self._user_id = str(kwargs.get("user_id") or "").strip()
+        self._user_name = str(kwargs.get("user_name") or "").strip()
+        self._chat_id = str(kwargs.get("chat_id") or "").strip()
+        self._chat_name = str(kwargs.get("chat_name") or "").strip()
+        self._chat_type = str(kwargs.get("chat_type") or "").strip()
+        self._thread_id = str(kwargs.get("thread_id") or "").strip()
+        self._agent_identity = str(kwargs.get("agent_identity") or "").strip()
+        self._turn_index = 0
+        self._session_turns = []
         self._mode = self._config.get("mode", "cloud")
         # "local" is a legacy alias for "local_embedded"
         if self._mode == "local":
@@ -513,7 +594,7 @@ class HindsightMemoryProvider(MemoryProvider):
         memory_mode = self._config.get("memory_mode", "hybrid")
         self._memory_mode = memory_mode if memory_mode in ("context", "tools", "hybrid") else "hybrid"
 
-        prefetch_method = self._config.get("recall_prefetch_method", "recall")
+        prefetch_method = self._config.get("recall_prefetch_method") or self._config.get("prefetch_method", "recall")
         self._prefetch_method = prefetch_method if prefetch_method in ("recall", "reflect") else "recall"
 
         # Bank options
@@ -521,9 +602,22 @@ class HindsightMemoryProvider(MemoryProvider):
         self._bank_retain_mission = self._config.get("bank_retain_mission") or None
 
         # Tags
-        self._tags = self._config.get("tags") or None
+        self._retain_tags = _normalize_retain_tags(
+            self._config.get("retain_tags")
+            or os.environ.get("HINDSIGHT_RETAIN_TAGS", "")
+        )
+        self._tags = self._retain_tags or None
         self._recall_tags = self._config.get("recall_tags") or None
         self._recall_tags_match = self._config.get("recall_tags_match", "any")
+        self._retain_source = str(
+            self._config.get("retain_source") or os.environ.get("HINDSIGHT_RETAIN_SOURCE", "")
+        ).strip()
+        self._retain_user_prefix = str(
+            self._config.get("retain_user_prefix") or os.environ.get("HINDSIGHT_RETAIN_USER_PREFIX", "User")
+        ).strip() or "User"
+        self._retain_assistant_prefix = str(
+            self._config.get("retain_assistant_prefix") or os.environ.get("HINDSIGHT_RETAIN_ASSISTANT_PREFIX", "Assistant")
+        ).strip() or "Assistant"
 
         # Retain controls
         self._auto_retain = self._config.get("auto_retain", True)
@@ -547,11 +641,9 @@ class HindsightMemoryProvider(MemoryProvider):
         logger.info("Hindsight initialized: mode=%s, api_url=%s, bank=%s, budget=%s, memory_mode=%s, prefetch_method=%s, client=%s",
                      self._mode, self._api_url, self._bank_id, self._budget, self._memory_mode, self._prefetch_method, _client_version)
         logger.debug("Hindsight config: auto_retain=%s, auto_recall=%s, retain_every_n=%d, "
-                     "retain_async=%s, retain_context=%s, "
-                     "recall_max_tokens=%d, recall_max_input_chars=%d, tags=%s, recall_tags=%s",
+                     "retain_async=%s, retain_context=%s, recall_max_tokens=%d, recall_max_input_chars=%d, tags=%s, recall_tags=%s",
                      self._auto_retain, self._auto_recall, self._retain_every_n_turns,
-                     self._retain_async, self._retain_context,
-                     self._recall_max_tokens, self._recall_max_input_chars,
+                     self._retain_async, self._retain_context, self._recall_max_tokens, self._recall_max_input_chars,
                      self._tags, self._recall_tags)
 
         # For local mode, start the embedded daemon in the background so it
@@ -712,6 +804,78 @@ class HindsightMemoryProvider(MemoryProvider):
         self._prefetch_thread = threading.Thread(target=_run, daemon=True, name="hindsight-prefetch")
         self._prefetch_thread.start()
 
+    def _build_turn_messages(self, user_content: str, assistant_content: str) -> List[Dict[str, str]]:
+        now = datetime.now(timezone.utc).isoformat()
+        return [
+            {
+                "role": "user",
+                "content": f"{self._retain_user_prefix}: {user_content}",
+                "timestamp": now,
+            },
+            {
+                "role": "assistant",
+                "content": f"{self._retain_assistant_prefix}: {assistant_content}",
+                "timestamp": now,
+            },
+        ]
+
+    def _build_metadata(self, *, message_count: int, turn_index: int) -> Dict[str, str]:
+        metadata: Dict[str, str] = {
+            "retained_at": _utc_timestamp(),
+            "message_count": str(message_count),
+            "turn_index": str(turn_index),
+        }
+        if self._retain_source:
+            metadata["source"] = self._retain_source
+        if self._session_id:
+            metadata["session_id"] = self._session_id
+        if self._platform:
+            metadata["platform"] = self._platform
+        if self._user_id:
+            metadata["user_id"] = self._user_id
+        if self._user_name:
+            metadata["user_name"] = self._user_name
+        if self._chat_id:
+            metadata["chat_id"] = self._chat_id
+        if self._chat_name:
+            metadata["chat_name"] = self._chat_name
+        if self._chat_type:
+            metadata["chat_type"] = self._chat_type
+        if self._thread_id:
+            metadata["thread_id"] = self._thread_id
+        if self._agent_identity:
+            metadata["agent_identity"] = self._agent_identity
+        return metadata
+
+    def _build_retain_kwargs(
+        self,
+        content: str,
+        *,
+        context: str | None = None,
+        document_id: str | None = None,
+        metadata: Dict[str, str] | None = None,
+        tags: List[str] | None = None,
+        retain_async: bool | None = None,
+    ) -> Dict[str, Any]:
+        kwargs: Dict[str, Any] = {
+            "bank_id": self._bank_id,
+            "content": content,
+            "metadata": metadata or self._build_metadata(message_count=1, turn_index=self._turn_index),
+        }
+        if context is not None:
+            kwargs["context"] = context
+        if document_id:
+            kwargs["document_id"] = document_id
+        if retain_async is not None:
+            kwargs["retain_async"] = retain_async
+        merged_tags = _normalize_retain_tags(self._retain_tags)
+        for tag in _normalize_retain_tags(tags):
+            if tag not in merged_tags:
+                merged_tags.append(tag)
+        if merged_tags:
+            kwargs["tags"] = merged_tags
+        return kwargs
+
     def sync_turn(self, user_content: str, assistant_content: str, *, session_id: str = "") -> None:
         """Retain conversation turn in background (non-blocking).
 
@@ -721,19 +885,14 @@ class HindsightMemoryProvider(MemoryProvider):
             logger.debug("sync_turn: skipped (auto_retain disabled)")
             return
 
-        from datetime import datetime, timezone
-        now = datetime.now(timezone.utc).isoformat()
+        if session_id:
+            self._session_id = str(session_id).strip()
 
-        messages = [
-            {"role": "user", "content": user_content, "timestamp": now},
-            {"role": "assistant", "content": assistant_content, "timestamp": now},
-        ]
-
-        turn = json.dumps(messages)
+        turn = json.dumps(self._build_turn_messages(user_content, assistant_content))
         self._session_turns.append(turn)
         self._turn_counter += 1
+        self._turn_index = self._turn_counter
 
-        # Only retain every N turns
         if self._turn_counter % self._retain_every_n_turns != 0:
             logger.debug("sync_turn: buffered turn %d (will retain at turn %d)",
                          self._turn_counter, self._turn_counter + (self._retain_every_n_turns - self._turn_counter % self._retain_every_n_turns))
@@ -741,19 +900,21 @@ class HindsightMemoryProvider(MemoryProvider):
 
         logger.debug("sync_turn: retaining %d turns, total session content %d chars",
                      len(self._session_turns), sum(len(t) for t in self._session_turns))
-        # Send the ENTIRE session as a single JSON array (document_id deduplicates).
-        # Each element in _session_turns is a JSON string of that turn's messages.
         content = "[" + ",".join(self._session_turns) + "]"
 
         def _sync():
             try:
                 client = self._get_client()
-                item: dict = {
-                    "content": content,
-                    "context": self._retain_context,
-                }
-                if self._tags:
-                    item["tags"] = self._tags
+                item = self._build_retain_kwargs(
+                    content,
+                    context=self._retain_context,
+                    metadata=self._build_metadata(
+                        message_count=len(self._session_turns) * 2,
+                        turn_index=self._turn_index,
+                    ),
+                )
+                item.pop("bank_id", None)
+                item.pop("retain_async", None)
                 logger.debug("Hindsight retain: bank=%s, doc=%s, async=%s, content_len=%d, num_turns=%d",
                              self._bank_id, self._session_id, self._retain_async, len(content), len(self._session_turns))
                 _run_sync(client.aretain_batch(
@@ -789,11 +950,11 @@ class HindsightMemoryProvider(MemoryProvider):
                 return tool_error("Missing required parameter: content")
             context = args.get("context")
             try:
-                retain_kwargs: dict = {
-                    "bank_id": self._bank_id, "content": content, "context": context,
-                }
-                if self._tags:
-                    retain_kwargs["tags"] = self._tags
+                retain_kwargs = self._build_retain_kwargs(
+                    content,
+                    context=context,
+                    tags=args.get("tags"),
+                )
                 logger.debug("Tool hindsight_retain: bank=%s, content_len=%d, context=%s",
                              self._bank_id, len(content), context)
                 _run_sync(client.aretain(**retain_kwargs))