{_html.escape(cmd_preview)}\n\n"
+ f"Reason: {_html.escape(description)}"
)
# Resolve thread context for thread replies
@@ -1163,7 +1161,7 @@ class TelegramAdapter(BasePlatformAdapter):
kwargs: Dict[str, Any] = {
"chat_id": int(chat_id),
"text": text,
- "parse_mode": ParseMode.MARKDOWN,
+ "parse_mode": ParseMode.HTML,
"reply_markup": keyboard,
**self._link_preview_kwargs(),
}
diff --git a/gateway/run.py b/gateway/run.py
index 3d86f1632f..31ae5988ae 100644
--- a/gateway/run.py
+++ b/gateway/run.py
@@ -131,6 +131,12 @@ if _config_path.exists():
for _cfg_key, _env_var in _terminal_env_map.items():
if _cfg_key in _terminal_cfg:
_val = _terminal_cfg[_cfg_key]
+ # Skip cwd placeholder values (".", "auto", "cwd") — the
+ # gateway resolves these to Path.home() later (line ~255).
+ # Writing the raw placeholder here would just be noise.
+ # Only bridge explicit absolute paths from config.yaml.
+ if _cfg_key == "cwd" and str(_val) in (".", "auto", "cwd"):
+ continue
if isinstance(_val, list):
os.environ[_env_var] = json.dumps(_val)
else:
@@ -225,6 +231,13 @@ try:
except Exception:
pass
+# Warn if user has deprecated MESSAGING_CWD / TERMINAL_CWD in .env
+try:
+ from hermes_cli.config import warn_deprecated_cwd_env_vars
+ warn_deprecated_cwd_env_vars()
+except Exception:
+ pass
+
# Gateway runs in quiet mode - suppress debug output and use cwd directly (no temp dirs)
os.environ["HERMES_QUIET"] = "1"
@@ -232,12 +245,14 @@ os.environ["HERMES_QUIET"] = "1"
os.environ["HERMES_EXEC_ASK"] = "1"
# Set terminal working directory for messaging platforms.
-# If the user set an explicit path in config.yaml (not "." or "auto"),
-# respect it. Otherwise use MESSAGING_CWD or default to home directory.
+# config.yaml terminal.cwd is the canonical source (bridged to TERMINAL_CWD
+# by the config bridge above). When it's unset or a placeholder, default
+# to home directory. MESSAGING_CWD is accepted as a backward-compat
+# fallback (deprecated — the warning above tells users to migrate).
_configured_cwd = os.environ.get("TERMINAL_CWD", "")
if not _configured_cwd or _configured_cwd in (".", "auto", "cwd"):
- messaging_cwd = os.getenv("MESSAGING_CWD") or str(Path.home())
- os.environ["TERMINAL_CWD"] = messaging_cwd
+ _fallback = os.getenv("MESSAGING_CWD") or str(Path.home())
+ os.environ["TERMINAL_CWD"] = _fallback
from gateway.config import (
Platform,
@@ -762,69 +777,72 @@ class GatewayRunner:
enabled_toolsets=["memory", "skills"],
session_id=old_session_id,
)
- # Fully silence the flush agent — quiet_mode only suppresses init
- # messages; tool call output still leaks to the terminal through
- # _safe_print → _print_fn. Set a no-op to prevent that.
- tmp_agent._print_fn = lambda *a, **kw: None
-
- # Build conversation history from transcript
- msgs = [
- {"role": m.get("role"), "content": m.get("content")}
- for m in history
- if m.get("role") in ("user", "assistant") and m.get("content")
- ]
-
- # Read live memory state from disk so the flush agent can see
- # what's already saved and avoid overwriting newer entries.
- _current_memory = ""
try:
- from tools.memory_tool import get_memory_dir
- _mem_dir = get_memory_dir()
- for fname, label in [
- ("MEMORY.md", "MEMORY (your personal notes)"),
- ("USER.md", "USER PROFILE (who the user is)"),
- ]:
- fpath = _mem_dir / fname
- if fpath.exists():
- content = fpath.read_text(encoding="utf-8").strip()
- if content:
- _current_memory += f"\n\n## Current {label}:\n{content}"
- except Exception:
- pass # Non-fatal — flush still works, just without the guard
+ # Fully silence the flush agent — quiet_mode only suppresses init
+ # messages; tool call output still leaks to the terminal through
+ # _safe_print → _print_fn. Set a no-op to prevent that.
+ tmp_agent._print_fn = lambda *a, **kw: None
- # Give the agent a real turn to think about what to save
- flush_prompt = (
- "[System: This session is about to be automatically reset due to "
- "inactivity or a scheduled daily reset. The conversation context "
- "will be cleared after this turn.\n\n"
- "Review the conversation above and:\n"
- "1. Save any important facts, preferences, or decisions to memory "
- "(user profile or your notes) that would be useful in future sessions.\n"
- "2. If you discovered a reusable workflow or solved a non-trivial "
- "problem, consider saving it as a skill.\n"
- "3. If nothing is worth saving, that's fine — just skip.\n\n"
- )
+ # Build conversation history from transcript
+ msgs = [
+ {"role": m.get("role"), "content": m.get("content")}
+ for m in history
+ if m.get("role") in ("user", "assistant") and m.get("content")
+ ]
- if _current_memory:
- flush_prompt += (
- "IMPORTANT — here is the current live state of memory. Other "
- "sessions, cron jobs, or the user may have updated it since this "
- "conversation ended. Do NOT overwrite or remove entries unless "
- "the conversation above reveals something that genuinely "
- "supersedes them. Only add new information that is not already "
- "captured below."
- f"{_current_memory}\n\n"
+ # Read live memory state from disk so the flush agent can see
+ # what's already saved and avoid overwriting newer entries.
+ _current_memory = ""
+ try:
+ from tools.memory_tool import get_memory_dir
+ _mem_dir = get_memory_dir()
+ for fname, label in [
+ ("MEMORY.md", "MEMORY (your personal notes)"),
+ ("USER.md", "USER PROFILE (who the user is)"),
+ ]:
+ fpath = _mem_dir / fname
+ if fpath.exists():
+ content = fpath.read_text(encoding="utf-8").strip()
+ if content:
+ _current_memory += f"\n\n## Current {label}:\n{content}"
+ except Exception:
+ pass # Non-fatal — flush still works, just without the guard
+
+ # Give the agent a real turn to think about what to save
+ flush_prompt = (
+ "[System: This session is about to be automatically reset due to "
+ "inactivity or a scheduled daily reset. The conversation context "
+ "will be cleared after this turn.\n\n"
+ "Review the conversation above and:\n"
+ "1. Save any important facts, preferences, or decisions to memory "
+ "(user profile or your notes) that would be useful in future sessions.\n"
+ "2. If you discovered a reusable workflow or solved a non-trivial "
+ "problem, consider saving it as a skill.\n"
+ "3. If nothing is worth saving, that's fine — just skip.\n\n"
)
- flush_prompt += (
- "Do NOT respond to the user. Just use the memory and skill_manage "
- "tools if needed, then stop.]"
- )
+ if _current_memory:
+ flush_prompt += (
+ "IMPORTANT — here is the current live state of memory. Other "
+ "sessions, cron jobs, or the user may have updated it since this "
+ "conversation ended. Do NOT overwrite or remove entries unless "
+ "the conversation above reveals something that genuinely "
+ "supersedes them. Only add new information that is not already "
+ "captured below."
+ f"{_current_memory}\n\n"
+ )
- tmp_agent.run_conversation(
- user_message=flush_prompt,
- conversation_history=msgs,
- )
+ flush_prompt += (
+ "Do NOT respond to the user. Just use the memory and skill_manage "
+ "tools if needed, then stop.]"
+ )
+
+ tmp_agent.run_conversation(
+ user_message=flush_prompt,
+ conversation_history=msgs,
+ )
+ finally:
+ self._cleanup_agent_resources(tmp_agent)
logger.info("Pre-reset memory flush completed for session %s", old_session_id)
except Exception as e:
logger.debug("Pre-reset memory flush failed for session %s: %s", old_session_id, e)
@@ -1562,19 +1580,25 @@ class GatewayRunner:
)
except Exception:
pass
- try:
- if hasattr(agent, "shutdown_memory_provider"):
- agent.shutdown_memory_provider()
- except Exception:
- pass
- # Close tool resources (terminal sandboxes, browser daemons,
- # background processes, httpx clients) to prevent zombie
- # process accumulation.
- try:
- if hasattr(agent, 'close'):
- agent.close()
- except Exception:
- pass
+ self._cleanup_agent_resources(agent)
+
+ def _cleanup_agent_resources(self, agent: Any) -> None:
+ """Best-effort cleanup for temporary or cached agent instances."""
+ if agent is None:
+ return
+ try:
+ if hasattr(agent, "shutdown_memory_provider"):
+ agent.shutdown_memory_provider()
+ except Exception:
+ pass
+ # Close tool resources (terminal sandboxes, browser daemons,
+ # background processes, httpx clients) to prevent zombie
+ # process accumulation.
+ try:
+ if hasattr(agent, "close"):
+ agent.close()
+ except Exception:
+ pass
_STUCK_LOOP_THRESHOLD = 3 # restarts while active before auto-suspend
_STUCK_LOOP_FILE = ".restart_failure_counts"
@@ -2077,16 +2101,7 @@ class GatewayRunner:
if _cached_agent is None:
_cached_agent = self._running_agents.get(key)
if _cached_agent and _cached_agent is not _AGENT_PENDING_SENTINEL:
- try:
- if hasattr(_cached_agent, 'shutdown_memory_provider'):
- _cached_agent.shutdown_memory_provider()
- except Exception:
- pass
- try:
- if hasattr(_cached_agent, 'close'):
- _cached_agent.close()
- except Exception:
- pass
+ self._cleanup_agent_resources(_cached_agent)
# Mark as flushed and persist to disk so the flag
# survives gateway restarts.
with self.session_store._lock:
@@ -3410,7 +3425,7 @@ class GatewayRunner:
from agent.context_references import preprocess_context_references_async
from agent.model_metadata import get_model_context_length
- _msg_cwd = os.environ.get("MESSAGING_CWD", os.path.expanduser("~"))
+ _msg_cwd = os.environ.get("TERMINAL_CWD", os.path.expanduser("~"))
_msg_ctx_len = get_model_context_length(
self._model,
base_url=self._base_url or "",
@@ -3782,51 +3797,54 @@ class GatewayRunner:
enabled_toolsets=["memory"],
session_id=session_entry.session_id,
)
- _hyg_agent._print_fn = lambda *a, **kw: None
+ try:
+ _hyg_agent._print_fn = lambda *a, **kw: None
- loop = asyncio.get_running_loop()
- _compressed, _ = await loop.run_in_executor(
- None,
- lambda: _hyg_agent._compress_context(
- _hyg_msgs, "",
- approx_tokens=_approx_tokens,
- ),
- )
-
- # _compress_context ends the old session and creates
- # a new session_id. Write compressed messages into
- # the NEW session so the old transcript stays intact
- # and searchable via session_search.
- _hyg_new_sid = _hyg_agent.session_id
- if _hyg_new_sid != session_entry.session_id:
- session_entry.session_id = _hyg_new_sid
- self.session_store._save()
-
- self.session_store.rewrite_transcript(
- session_entry.session_id, _compressed
- )
- # Reset stored token count — transcript was rewritten
- session_entry.last_prompt_tokens = 0
- history = _compressed
- _new_count = len(_compressed)
- _new_tokens = estimate_messages_tokens_rough(
- _compressed
- )
-
- logger.info(
- "Session hygiene: compressed %s → %s msgs, "
- "~%s → ~%s tokens",
- _msg_count, _new_count,
- f"{_approx_tokens:,}", f"{_new_tokens:,}",
- )
-
- if _new_tokens >= _warn_token_threshold:
- logger.warning(
- "Session hygiene: still ~%s tokens after "
- "compression",
- f"{_new_tokens:,}",
+ loop = asyncio.get_running_loop()
+ _compressed, _ = await loop.run_in_executor(
+ None,
+ lambda: _hyg_agent._compress_context(
+ _hyg_msgs, "",
+ approx_tokens=_approx_tokens,
+ ),
)
+ # _compress_context ends the old session and creates
+ # a new session_id. Write compressed messages into
+ # the NEW session so the old transcript stays intact
+ # and searchable via session_search.
+ _hyg_new_sid = _hyg_agent.session_id
+ if _hyg_new_sid != session_entry.session_id:
+ session_entry.session_id = _hyg_new_sid
+ self.session_store._save()
+
+ self.session_store.rewrite_transcript(
+ session_entry.session_id, _compressed
+ )
+ # Reset stored token count — transcript was rewritten
+ session_entry.last_prompt_tokens = 0
+ history = _compressed
+ _new_count = len(_compressed)
+ _new_tokens = estimate_messages_tokens_rough(
+ _compressed
+ )
+
+ logger.info(
+ "Session hygiene: compressed %s → %s msgs, "
+ "~%s → ~%s tokens",
+ _msg_count, _new_count,
+ f"{_approx_tokens:,}", f"{_new_tokens:,}",
+ )
+
+ if _new_tokens >= _warn_token_threshold:
+ logger.warning(
+ "Session hygiene: still ~%s tokens after "
+ "compression",
+ f"{_new_tokens:,}",
+ )
+ finally:
+ self._cleanup_agent_resources(_hyg_agent)
+
except Exception as e:
logger.warning(
"Session hygiene auto-compress failed: %s", e
@@ -4344,16 +4362,7 @@ class GatewayRunner:
_cached = self._agent_cache.get(session_key)
_old_agent = _cached[0] if isinstance(_cached, tuple) else _cached if _cached else None
if _old_agent is not None:
- try:
- if hasattr(_old_agent, "shutdown_memory_provider"):
- _old_agent.shutdown_memory_provider()
- except Exception:
- pass
- try:
- if hasattr(_old_agent, "close"):
- _old_agent.close()
- except Exception:
- pass
+ self._cleanup_agent_resources(_old_agent)
self._evict_cached_agent(session_key)
try:
@@ -5717,7 +5726,7 @@ class GatewayRunner:
max_snapshots=cp_cfg.get("max_snapshots", 50),
)
- cwd = os.getenv("MESSAGING_CWD", str(Path.home()))
+ cwd = os.getenv("TERMINAL_CWD", str(Path.home()))
arg = event.get_command_args().strip()
if not arg:
@@ -5838,11 +5847,13 @@ class GatewayRunner:
session_db=self._session_db,
fallback_model=self._fallback_model,
)
-
- return agent.run_conversation(
- user_message=prompt,
- task_id=task_id,
- )
+ try:
+ return agent.run_conversation(
+ user_message=prompt,
+ task_id=task_id,
+ )
+ finally:
+ self._cleanup_agent_resources(agent)
result = await self._run_in_executor_with_context(run_sync)
@@ -6020,11 +6031,14 @@ class GatewayRunner:
skip_context_files=True,
persist_session=False,
)
- return agent.run_conversation(
- user_message=btw_prompt,
- conversation_history=history_snapshot,
- task_id=task_id,
- )
+ try:
+ return agent.run_conversation(
+ user_message=btw_prompt,
+ conversation_history=history_snapshot,
+ task_id=task_id,
+ )
+ finally:
+ self._cleanup_agent_resources(agent)
result = await self._run_in_executor_with_context(run_sync)
@@ -6353,42 +6367,45 @@ class GatewayRunner:
enabled_toolsets=["memory"],
session_id=session_entry.session_id,
)
- tmp_agent._print_fn = lambda *a, **kw: None
+ try:
+ tmp_agent._print_fn = lambda *a, **kw: None
- compressor = tmp_agent.context_compressor
- compress_start = compressor.protect_first_n
- compress_start = compressor._align_boundary_forward(msgs, compress_start)
- compress_end = compressor._find_tail_cut_by_tokens(msgs, compress_start)
- if compress_start >= compress_end:
- return "Nothing to compress yet (the transcript is still all protected context)."
+ compressor = tmp_agent.context_compressor
+ compress_start = compressor.protect_first_n
+ compress_start = compressor._align_boundary_forward(msgs, compress_start)
+ compress_end = compressor._find_tail_cut_by_tokens(msgs, compress_start)
+ if compress_start >= compress_end:
+ return "Nothing to compress yet (the transcript is still all protected context)."
- loop = asyncio.get_running_loop()
- compressed, _ = await loop.run_in_executor(
- None,
- lambda: tmp_agent._compress_context(msgs, "", approx_tokens=approx_tokens, focus_topic=focus_topic)
- )
+ loop = asyncio.get_running_loop()
+ compressed, _ = await loop.run_in_executor(
+ None,
+ lambda: tmp_agent._compress_context(msgs, "", approx_tokens=approx_tokens, focus_topic=focus_topic)
+ )
- # _compress_context already calls end_session() on the old session
- # (preserving its full transcript in SQLite) and creates a new
- # session_id for the continuation. Write the compressed messages
- # into the NEW session so the original history stays searchable.
- new_session_id = tmp_agent.session_id
- if new_session_id != session_entry.session_id:
- session_entry.session_id = new_session_id
- self.session_store._save()
+ # _compress_context already calls end_session() on the old session
+ # (preserving its full transcript in SQLite) and creates a new
+ # session_id for the continuation. Write the compressed messages
+ # into the NEW session so the original history stays searchable.
+ new_session_id = tmp_agent.session_id
+ if new_session_id != session_entry.session_id:
+ session_entry.session_id = new_session_id
+ self.session_store._save()
- self.session_store.rewrite_transcript(new_session_id, compressed)
- # Reset stored token count — transcript changed, old value is stale
- self.session_store.update_session(
- session_entry.session_key, last_prompt_tokens=0
- )
- new_tokens = estimate_messages_tokens_rough(compressed)
- summary = summarize_manual_compression(
- msgs,
- compressed,
- approx_tokens,
- new_tokens,
- )
+ self.session_store.rewrite_transcript(new_session_id, compressed)
+ # Reset stored token count — transcript changed, old value is stale
+ self.session_store.update_session(
+ session_entry.session_key, last_prompt_tokens=0
+ )
+ new_tokens = estimate_messages_tokens_rough(compressed)
+ summary = summarize_manual_compression(
+ msgs,
+ compressed,
+ approx_tokens,
+ new_tokens,
+ )
+ finally:
+ self._cleanup_agent_resources(tmp_agent)
lines = [f"🗜️ {summary['headline']}"]
if focus_topic:
lines.append(f"Focus: \"{focus_topic}\"")
@@ -8896,7 +8913,7 @@ class GatewayRunner:
# false positives from MagicMock auto-attribute creation in tests.
if getattr(type(_status_adapter), "send_exec_approval", None) is not None:
try:
- asyncio.run_coroutine_threadsafe(
+ _approval_result = asyncio.run_coroutine_threadsafe(
_status_adapter.send_exec_approval(
chat_id=_status_chat_id,
command=cmd,
@@ -8906,7 +8923,12 @@ class GatewayRunner:
),
_loop_for_step,
).result(timeout=15)
- return
+ if _approval_result.success:
+ return
+ logger.warning(
+ "Button-based approval failed (send returned error), falling back to text: %s",
+ _approval_result.error,
+ )
except Exception as _e:
logger.warning(
"Button-based approval failed, falling back to text: %s", _e
@@ -9536,6 +9558,7 @@ class GatewayRunner:
next_source = source
next_message = pending
next_message_id = None
+ next_channel_prompt = None
if pending_event is not None:
next_source = getattr(pending_event, "source", None) or source
next_message = await self._prepare_inbound_message_text(
@@ -9546,6 +9569,7 @@ class GatewayRunner:
if next_message is None:
return result
next_message_id = getattr(pending_event, "message_id", None)
+ next_channel_prompt = getattr(pending_event, "channel_prompt", None)
# Restart typing indicator so the user sees activity while
# the follow-up turn runs. The outer _process_message_background
@@ -9569,7 +9593,7 @@ class GatewayRunner:
session_key=session_key,
_interrupt_depth=_interrupt_depth + 1,
event_message_id=next_message_id,
- channel_prompt=pending_event.channel_prompt,
+ channel_prompt=next_channel_prompt,
)
finally:
# Stop progress sender, interrupt monitor, and notification task
diff --git a/gateway/stream_consumer.py b/gateway/stream_consumer.py
index a644547e6a..853b159034 100644
--- a/gateway/stream_consumer.py
+++ b/gateway/stream_consumer.py
@@ -515,9 +515,17 @@ class GatewayStreamConsumer:
self._fallback_final_send = False
if not continuation.strip():
# Nothing new to send — the visible partial already matches final text.
- self._already_sent = True
- self._final_response_sent = True
- return
+ # BUT: if final_text itself has meaningful content (e.g. a timeout
+ # message after a long tool call), the prefix-based continuation
+ # calculation may wrongly conclude "already shown" because the
+ # streamed prefix was from a *previous* segment (before the tool
+ # boundary). In that case, send the full final_text as-is (#10807).
+ if final_text.strip() and final_text != self._visible_prefix():
+ continuation = final_text
+ else:
+ self._already_sent = True
+ self._final_response_sent = True
+ return
raw_limit = getattr(self.adapter, "MAX_MESSAGE_LENGTH", 4096)
safe_limit = max(500, raw_limit - 100)
diff --git a/hermes_cli/config.py b/hermes_cli/config.py
index a9f55f4c57..33bc325ee3 100644
--- a/hermes_cli/config.py
+++ b/hermes_cli/config.py
@@ -1597,13 +1597,8 @@ OPTIONAL_ENV_VARS = {
},
# ── Agent settings ──
- "MESSAGING_CWD": {
- "description": "Working directory for terminal commands via messaging",
- "prompt": "Messaging working directory (default: home)",
- "url": None,
- "password": False,
- "category": "setting",
- },
+ # NOTE: MESSAGING_CWD was removed here — use terminal.cwd in config.yaml
+ # instead. The gateway reads TERMINAL_CWD (bridged from terminal.cwd).
"SUDO_PASSWORD": {
"description": "Sudo password for terminal commands requiring root access; set to an explicit empty string to try empty without prompting",
"prompt": "Sudo password",
@@ -2082,6 +2077,52 @@ def print_config_warnings(config: Optional[Dict[str, Any]] = None) -> None:
sys.stderr.write("\n".join(lines) + "\n\n")
+def warn_deprecated_cwd_env_vars(config: Optional[Dict[str, Any]] = None) -> None:
+ """Warn if MESSAGING_CWD or TERMINAL_CWD is set in .env instead of config.yaml.
+
+ These env vars are deprecated — the canonical setting is terminal.cwd
+ in config.yaml. Prints a migration hint to stderr.
+ """
+ import os, sys
+ messaging_cwd = os.environ.get("MESSAGING_CWD")
+ terminal_cwd_env = os.environ.get("TERMINAL_CWD")
+
+ if config is None:
+ try:
+ config = load_config()
+ except Exception:
+ return
+
+ terminal_cfg = config.get("terminal", {})
+ config_cwd = terminal_cfg.get("cwd", ".") if isinstance(terminal_cfg, dict) else "."
+ # Only warn if config.yaml doesn't have an explicit path
+ config_has_explicit_cwd = config_cwd not in (".", "auto", "cwd", "")
+
+ lines: list[str] = []
+ if messaging_cwd:
+ lines.append(
+ f" \033[33m⚠\033[0m MESSAGING_CWD={messaging_cwd} found in .env — "
+ f"this is deprecated."
+ )
+ if terminal_cwd_env and not config_has_explicit_cwd:
+ # TERMINAL_CWD in env but not from config bridge — likely from .env
+ lines.append(
+ f" \033[33m⚠\033[0m TERMINAL_CWD={terminal_cwd_env} found in .env — "
+ f"this is deprecated."
+ )
+ if lines:
+ hint_path = os.environ.get("HERMES_HOME", "~/.hermes")
+ lines.insert(0, "\033[33m⚠ Deprecated .env settings detected:\033[0m")
+ lines.append(
+ f" \033[2mMove to config.yaml instead: "
+ f"terminal:\\n cwd: /your/project/path\033[0m"
+ )
+ lines.append(
+ f" \033[2mThen remove the old entries from {hint_path}/.env\033[0m"
+ )
+ sys.stderr.write("\n".join(lines) + "\n\n")
+
+
def migrate_config(interactive: bool = True, quiet: bool = False) -> Dict[str, Any]:
"""
Migrate config to latest version, prompting for new required fields.
diff --git a/hermes_cli/main.py b/hermes_cli/main.py
index a9ad311877..15a20edf14 100644
--- a/hermes_cli/main.py
+++ b/hermes_cli/main.py
@@ -5998,6 +5998,18 @@ Examples:
memory_sub.add_parser("setup", help="Interactive provider selection and configuration")
memory_sub.add_parser("status", help="Show current memory provider config")
memory_sub.add_parser("off", help="Disable external provider (built-in only)")
+ _reset_parser = memory_sub.add_parser(
+ "reset",
+ help="Erase all built-in memory (MEMORY.md and USER.md)",
+ )
+ _reset_parser.add_argument(
+ "--yes", "-y", action="store_true",
+ help="Skip confirmation prompt",
+ )
+ _reset_parser.add_argument(
+ "--target", choices=["all", "memory", "user"], default="all",
+ help="Which store to reset: 'all' (default), 'memory', or 'user'",
+ )
def cmd_memory(args):
sub = getattr(args, "memory_command", None)
@@ -6010,6 +6022,44 @@ Examples:
save_config(config)
print("\n ✓ Memory provider: built-in only")
print(" Saved to config.yaml\n")
+ elif sub == "reset":
+ from hermes_constants import get_hermes_home, display_hermes_home
+ mem_dir = get_hermes_home() / "memories"
+ target = getattr(args, "target", "all")
+ files_to_reset = []
+ if target in ("all", "memory"):
+ files_to_reset.append(("MEMORY.md", "agent notes"))
+ if target in ("all", "user"):
+ files_to_reset.append(("USER.md", "user profile"))
+
+ # Check what exists
+ existing = [(f, desc) for f, desc in files_to_reset if (mem_dir / f).exists()]
+ if not existing:
+ print(f"\n Nothing to reset — no memory files found in {display_hermes_home()}/memories/\n")
+ return
+
+ print(f"\n This will permanently erase the following memory files:")
+ for f, desc in existing:
+ path = mem_dir / f
+ size = path.stat().st_size
+ print(f" ◆ {f} ({desc}) — {size:,} bytes")
+
+ if not getattr(args, "yes", False):
+ try:
+ answer = input("\n Type 'yes' to confirm: ").strip().lower()
+ except (EOFError, KeyboardInterrupt):
+ print("\n Cancelled.\n")
+ return
+ if answer != "yes":
+ print(" Cancelled.\n")
+ return
+
+ for f, desc in existing:
+ (mem_dir / f).unlink()
+ print(f" ✓ Deleted {f} ({desc})")
+
+ print(f"\n Memory reset complete. New sessions will start with a blank slate.")
+ print(f" Files were in: {display_hermes_home()}/memories/\n")
else:
from hermes_cli.memory_setup import memory_command
memory_command(args)
diff --git a/hermes_cli/model_switch.py b/hermes_cli/model_switch.py
index 8ab00b2145..fe56506e28 100644
--- a/hermes_cli/model_switch.py
+++ b/hermes_cli/model_switch.py
@@ -807,6 +807,10 @@ def list_authenticated_providers(
# "nous" shares OpenRouter's curated list if not separately defined
if "nous" not in curated:
curated["nous"] = curated["openrouter"]
+ # Ollama Cloud uses dynamic discovery (no static curated list)
+ if "ollama-cloud" not in curated:
+ from hermes_cli.models import fetch_ollama_cloud_models
+ curated["ollama-cloud"] = fetch_ollama_cloud_models()
# --- 1. Check Hermes-mapped providers ---
for hermes_id, mdev_id in PROVIDER_TO_MODELS_DEV.items():
diff --git a/hermes_cli/models.py b/hermes_cli/models.py
index c6b2db571b..284cb0a39c 100644
--- a/hermes_cli/models.py
+++ b/hermes_cli/models.py
@@ -1044,7 +1044,7 @@ def detect_provider_for_model(
return (resolved_provider, default_models[0])
# Aggregators list other providers' models — never auto-switch TO them
- _AGGREGATORS = {"nous", "openrouter"}
+ _AGGREGATORS = {"nous", "openrouter", "ai-gateway", "copilot", "kilocode"}
# If the model belongs to the current provider's catalog, don't suggest switching
current_models = _PROVIDER_MODELS.get(current_provider, [])
@@ -1286,6 +1286,10 @@ def provider_model_ids(provider: Optional[str], *, force_refresh: bool = False)
live = _fetch_ai_gateway_models()
if live:
return live
+ if normalized == "ollama-cloud":
+ live = fetch_ollama_cloud_models(force_refresh=force_refresh)
+ if live:
+ return live
if normalized == "custom":
base_url = _get_custom_base_url()
if base_url:
diff --git a/hermes_cli/skin_engine.py b/hermes_cli/skin_engine.py
index 5b406f1f56..4222a966ef 100644
--- a/hermes_cli/skin_engine.py
+++ b/hermes_cli/skin_engine.py
@@ -708,7 +708,9 @@ def init_skin_from_config(config: dict) -> None:
Call this once during CLI init with the loaded config dict.
"""
- display = config.get("display", {})
+ display = config.get("display") or {}
+ if not isinstance(display, dict):
+ display = {}
skin_name = display.get("skin", "default")
if isinstance(skin_name, str) and skin_name.strip():
set_active_skin(skin_name.strip())
diff --git a/landingpage/apple-touch-icon.png b/landingpage/apple-touch-icon.png
deleted file mode 100644
index c5da175f8e..0000000000
Binary files a/landingpage/apple-touch-icon.png and /dev/null differ
diff --git a/landingpage/favicon-16x16.png b/landingpage/favicon-16x16.png
deleted file mode 100644
index 5bc67ef224..0000000000
Binary files a/landingpage/favicon-16x16.png and /dev/null differ
diff --git a/landingpage/favicon-32x32.png b/landingpage/favicon-32x32.png
deleted file mode 100644
index 8db2977a5b..0000000000
Binary files a/landingpage/favicon-32x32.png and /dev/null differ
diff --git a/landingpage/favicon.ico b/landingpage/favicon.ico
deleted file mode 100644
index 8586c395f6..0000000000
Binary files a/landingpage/favicon.ico and /dev/null differ
diff --git a/landingpage/hermes-agent-banner.png b/landingpage/hermes-agent-banner.png
deleted file mode 100644
index 2c4a160ceb..0000000000
Binary files a/landingpage/hermes-agent-banner.png and /dev/null differ
diff --git a/landingpage/icon-192.png b/landingpage/icon-192.png
deleted file mode 100644
index 126a395793..0000000000
Binary files a/landingpage/icon-192.png and /dev/null differ
diff --git a/landingpage/icon-512.png b/landingpage/icon-512.png
deleted file mode 100644
index c5b4c63a57..0000000000
Binary files a/landingpage/icon-512.png and /dev/null differ
diff --git a/landingpage/index.html b/landingpage/index.html
deleted file mode 100644
index e24ed11c48..0000000000
--- a/landingpage/index.html
+++ /dev/null
@@ -1,665 +0,0 @@
-
-
-
-
-
- - It's not a coding copilot tethered to an IDE or a chatbot wrapper - around a single API. It's an autonomous agent that - lives on your server, remembers what it learns, and gets more capable - the longer it runs. -
- -- Works on Linux, macOS & WSL2 · No prerequisites · Installs - everything automatically -
-curl -fsSL https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.sh | bash- Installs uv, Python 3.11, clones the repo, sets up everything. - No sudo needed. -
-# Interactive setup wizard
-hermes setup
-
-# Or choose your model
-hermes model- Connect to Nous Portal (OAuth), OpenRouter (API key), or your - own endpoint. -
-hermes- That's it. Full interactive CLI with tools, memory, and skills. -
-# Interactive gateway setup wizard
-hermes gateway setup
-
-# Start the messaging gateway
-hermes gateway
-
-# Install as a system service
-hermes gateway install- Walk through connecting Telegram, Discord, Slack, or WhatsApp. - Runs as a systemd service. -
-hermes update- Pulls the latest changes and reinstalls dependencies. Run - anytime to get new features and fixes. -
-- Native Windows support is extremely experimental and unsupported. - Please install - WSL2 - and run Hermes Agent from there. -
-- Telegram, Discord, Slack, WhatsApp, and CLI from a single gateway - — start on one, pick up on another. -
-- Persistent memory and auto-generated skills — it learns your - projects and never forgets how it solved a problem. -
-- Natural language cron scheduling for reports, backups, and - briefings — running unattended through the gateway. -
-- Isolated subagents with their own conversations, terminals, and - Python RPC scripts for zero-context-cost pipelines. -
-- Five backends — local, Docker, SSH, Singularity, Modal — with - container hardening and namespace isolation. -
-- Web search, browser automation, vision, image generation, - text-to-speech, and multi-model reasoning. -
-- 40+ built-in — web search, terminal, file system, browser - automation, vision, image generation, text-to-speech, code - execution, subagent delegation, memory, task planning, cron - scheduling, multi-model reasoning, and more. -
-- Telegram, Discord, Slack, WhatsApp, Signal, Email, and CLI — all - from a single gateway. Connect to - Nous Portal, OpenRouter, or any OpenAI-compatible API. -
-- Run locally, in Docker, over SSH, on Modal, Daytona, or - Singularity. Container hardening with read-only root, dropped - capabilities, and namespace isolation. -
-- 40+ bundled skills covering MLOps, GitHub workflows, research, - and more. The agent creates new skills on the fly and shares - them via the open - agentskills.io - format. Install community skills from - ClawHub, - LobeHub, and GitHub. -
-- Batch trajectory generation with parallel workers and - checkpointing. Atropos integration for RL training. Export to - ShareGPT for fine-tuning with trajectory compression. -
-