c886333d32
Replaces the unsafe 128K fallback for unknown models with a descending probe strategy (2M → 1M → 512K → 200K → 128K → 64K → 32K). When a context-length error occurs, the agent steps down tiers and retries. The discovered limit is cached per model+provider combo in ~/.hermes/context_length_cache.yaml so subsequent sessions skip probing. Also parses API error messages to extract the actual context limit (e.g. 'maximum context length is 32768 tokens') for instant resolution. The CLI banner now displays the context window size next to the model name (e.g. 'claude-opus-4 · 200K context · Nous Research'). Changes: - agent/model_metadata.py: CONTEXT_PROBE_TIERS, persistent cache (save/load/get), parse_context_limit_from_error(), get_next_probe_tier() - agent/context_compressor.py: accepts base_url, passes to metadata - run_agent.py: step-down logic in context error handler, caches on success - cli.py + hermes_cli/banner.py: context length in welcome banner - tests: 22 new tests for probing, parsing, and caching Addresses #132. PR #319's approach (8K default) rejected — too conservative.
276 lines
13 KiB
Python
276 lines
13 KiB
Python
"""Welcome banner, ASCII art, and skills summary for the CLI.
|
|
|
|
Pure display functions with no HermesCLI state dependency.
|
|
"""
|
|
|
|
from pathlib import Path
|
|
from typing import Dict, List, Any
|
|
|
|
from rich.console import Console
|
|
from rich.panel import Panel
|
|
from rich.table import Table
|
|
|
|
from prompt_toolkit import print_formatted_text as _pt_print
|
|
from prompt_toolkit.formatted_text import ANSI as _PT_ANSI
|
|
|
|
|
|
# =========================================================================
|
|
# ANSI building blocks for conversation display
|
|
# =========================================================================
|
|
|
|
_GOLD = "\033[1;33m"
|
|
_BOLD = "\033[1m"
|
|
_DIM = "\033[2m"
|
|
_RST = "\033[0m"
|
|
|
|
|
|
def cprint(text: str):
|
|
"""Print ANSI-colored text through prompt_toolkit's renderer."""
|
|
_pt_print(_PT_ANSI(text))
|
|
|
|
|
|
# =========================================================================
|
|
# ASCII Art & Branding
|
|
# =========================================================================
|
|
|
|
from hermes_cli import __version__ as VERSION
|
|
|
|
HERMES_AGENT_LOGO = """[bold #FFD700]██╗ ██╗███████╗██████╗ ███╗ ███╗███████╗███████╗ █████╗ ██████╗ ███████╗███╗ ██╗████████╗[/]
|
|
[bold #FFD700]██║ ██║██╔════╝██╔══██╗████╗ ████║██╔════╝██╔════╝ ██╔══██╗██╔════╝ ██╔════╝████╗ ██║╚══██╔══╝[/]
|
|
[#FFBF00]███████║█████╗ ██████╔╝██╔████╔██║█████╗ ███████╗█████╗███████║██║ ███╗█████╗ ██╔██╗ ██║ ██║[/]
|
|
[#FFBF00]██╔══██║██╔══╝ ██╔══██╗██║╚██╔╝██║██╔══╝ ╚════██║╚════╝██╔══██║██║ ██║██╔══╝ ██║╚██╗██║ ██║[/]
|
|
[#CD7F32]██║ ██║███████╗██║ ██║██║ ╚═╝ ██║███████╗███████║ ██║ ██║╚██████╔╝███████╗██║ ╚████║ ██║[/]
|
|
[#CD7F32]╚═╝ ╚═╝╚══════╝╚═╝ ╚═╝╚═╝ ╚═╝╚══════╝╚══════╝ ╚═╝ ╚═╝ ╚═════╝ ╚══════╝╚═╝ ╚═══╝ ╚═╝[/]"""
|
|
|
|
HERMES_CADUCEUS = """[#CD7F32]⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⢀⣀⡀⠀⣀⣀⠀⢀⣀⡀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀[/]
|
|
[#CD7F32]⠀⠀⠀⠀⠀⠀⢀⣠⣴⣾⣿⣿⣇⠸⣿⣿⠇⣸⣿⣿⣷⣦⣄⡀⠀⠀⠀⠀⠀⠀[/]
|
|
[#FFBF00]⠀⢀⣠⣴⣶⠿⠋⣩⡿⣿⡿⠻⣿⡇⢠⡄⢸⣿⠟⢿⣿⢿⣍⠙⠿⣶⣦⣄⡀⠀[/]
|
|
[#FFBF00]⠀⠀⠉⠉⠁⠶⠟⠋⠀⠉⠀⢀⣈⣁⡈⢁⣈⣁⡀⠀⠉⠀⠙⠻⠶⠈⠉⠉⠀⠀[/]
|
|
[#FFD700]⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⣴⣿⡿⠛⢁⡈⠛⢿⣿⣦⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀[/]
|
|
[#FFD700]⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠿⣿⣦⣤⣈⠁⢠⣴⣿⠿⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀[/]
|
|
[#FFBF00]⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠈⠉⠻⢿⣿⣦⡉⠁⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀[/]
|
|
[#FFBF00]⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠘⢷⣦⣈⠛⠃⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀[/]
|
|
[#CD7F32]⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⢠⣴⠦⠈⠙⠿⣦⡄⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀[/]
|
|
[#CD7F32]⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠸⣿⣤⡈⠁⢤⣿⠇⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀[/]
|
|
[#B8860B]⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠉⠛⠷⠄⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀[/]
|
|
[#B8860B]⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⢀⣀⠑⢶⣄⡀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀[/]
|
|
[#B8860B]⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⣿⠁⢰⡆⠈⡿⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀[/]
|
|
[#B8860B]⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠈⠳⠈⣡⠞⠁⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀[/]
|
|
[#B8860B]⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠈⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀[/]"""
|
|
|
|
COMPACT_BANNER = """
|
|
[bold #FFD700]╔══════════════════════════════════════════════════════════════╗[/]
|
|
[bold #FFD700]║[/] [#FFBF00]⚕ NOUS HERMES[/] [dim #B8860B]- AI Agent Framework[/] [bold #FFD700]║[/]
|
|
[bold #FFD700]║[/] [#CD7F32]Messenger of the Digital Gods[/] [dim #B8860B]Nous Research[/] [bold #FFD700]║[/]
|
|
[bold #FFD700]╚══════════════════════════════════════════════════════════════╝[/]
|
|
"""
|
|
|
|
|
|
# =========================================================================
|
|
# Skills scanning
|
|
# =========================================================================
|
|
|
|
def get_available_skills() -> Dict[str, List[str]]:
|
|
"""Scan ~/.hermes/skills/ and return skills grouped by category."""
|
|
import os
|
|
|
|
hermes_home = Path(os.getenv("HERMES_HOME", Path.home() / ".hermes"))
|
|
skills_dir = hermes_home / "skills"
|
|
skills_by_category = {}
|
|
|
|
if not skills_dir.exists():
|
|
return skills_by_category
|
|
|
|
for skill_file in skills_dir.rglob("SKILL.md"):
|
|
rel_path = skill_file.relative_to(skills_dir)
|
|
parts = rel_path.parts
|
|
if len(parts) >= 2:
|
|
category = parts[0]
|
|
skill_name = parts[-2]
|
|
else:
|
|
category = "general"
|
|
skill_name = skill_file.parent.name
|
|
skills_by_category.setdefault(category, []).append(skill_name)
|
|
|
|
return skills_by_category
|
|
|
|
|
|
# =========================================================================
|
|
# Welcome banner
|
|
# =========================================================================
|
|
|
|
def _format_context_length(tokens: int) -> str:
|
|
"""Format a token count for display (e.g. 128000 → '128K', 1048576 → '1M')."""
|
|
if tokens >= 1_000_000:
|
|
val = tokens / 1_000_000
|
|
return f"{val:g}M"
|
|
elif tokens >= 1_000:
|
|
val = tokens / 1_000
|
|
return f"{val:g}K"
|
|
return str(tokens)
|
|
|
|
|
|
def build_welcome_banner(console: Console, model: str, cwd: str,
|
|
tools: List[dict] = None,
|
|
enabled_toolsets: List[str] = None,
|
|
session_id: str = None,
|
|
get_toolset_for_tool=None,
|
|
context_length: int = None):
|
|
"""Build and print a welcome banner with caduceus on left and info on right.
|
|
|
|
Args:
|
|
console: Rich Console instance.
|
|
model: Current model name.
|
|
cwd: Current working directory.
|
|
tools: List of tool definitions.
|
|
enabled_toolsets: List of enabled toolset names.
|
|
session_id: Session identifier.
|
|
get_toolset_for_tool: Callable to map tool name -> toolset name.
|
|
context_length: Model's context window size in tokens.
|
|
"""
|
|
from model_tools import check_tool_availability, TOOLSET_REQUIREMENTS
|
|
if get_toolset_for_tool is None:
|
|
from model_tools import get_toolset_for_tool
|
|
|
|
tools = tools or []
|
|
enabled_toolsets = enabled_toolsets or []
|
|
|
|
_, unavailable_toolsets = check_tool_availability(quiet=True)
|
|
disabled_tools = set()
|
|
for item in unavailable_toolsets:
|
|
disabled_tools.update(item.get("tools", []))
|
|
|
|
layout_table = Table.grid(padding=(0, 2))
|
|
layout_table.add_column("left", justify="center")
|
|
layout_table.add_column("right", justify="left")
|
|
|
|
left_lines = ["", HERMES_CADUCEUS, ""]
|
|
model_short = model.split("/")[-1] if "/" in model else model
|
|
if len(model_short) > 28:
|
|
model_short = model_short[:25] + "..."
|
|
ctx_str = f" [dim #B8860B]·[/] [dim #B8860B]{_format_context_length(context_length)} context[/]" if context_length else ""
|
|
left_lines.append(f"[#FFBF00]{model_short}[/]{ctx_str} [dim #B8860B]·[/] [dim #B8860B]Nous Research[/]")
|
|
left_lines.append(f"[dim #B8860B]{cwd}[/]")
|
|
if session_id:
|
|
left_lines.append(f"[dim #8B8682]Session: {session_id}[/]")
|
|
left_content = "\n".join(left_lines)
|
|
|
|
right_lines = ["[bold #FFBF00]Available Tools[/]"]
|
|
toolsets_dict: Dict[str, list] = {}
|
|
|
|
for tool in tools:
|
|
tool_name = tool["function"]["name"]
|
|
toolset = get_toolset_for_tool(tool_name) or "other"
|
|
toolsets_dict.setdefault(toolset, []).append(tool_name)
|
|
|
|
for item in unavailable_toolsets:
|
|
toolset_id = item.get("id", item.get("name", "unknown"))
|
|
display_name = f"{toolset_id}_tools" if not toolset_id.endswith("_tools") else toolset_id
|
|
if display_name not in toolsets_dict:
|
|
toolsets_dict[display_name] = []
|
|
for tool_name in item.get("tools", []):
|
|
if tool_name not in toolsets_dict[display_name]:
|
|
toolsets_dict[display_name].append(tool_name)
|
|
|
|
sorted_toolsets = sorted(toolsets_dict.keys())
|
|
display_toolsets = sorted_toolsets[:8]
|
|
remaining_toolsets = len(sorted_toolsets) - 8
|
|
|
|
for toolset in display_toolsets:
|
|
tool_names = toolsets_dict[toolset]
|
|
colored_names = []
|
|
for name in sorted(tool_names):
|
|
if name in disabled_tools:
|
|
colored_names.append(f"[red]{name}[/]")
|
|
else:
|
|
colored_names.append(f"[#FFF8DC]{name}[/]")
|
|
|
|
tools_str = ", ".join(colored_names)
|
|
if len(", ".join(sorted(tool_names))) > 45:
|
|
short_names = []
|
|
length = 0
|
|
for name in sorted(tool_names):
|
|
if length + len(name) + 2 > 42:
|
|
short_names.append("...")
|
|
break
|
|
short_names.append(name)
|
|
length += len(name) + 2
|
|
colored_names = []
|
|
for name in short_names:
|
|
if name == "...":
|
|
colored_names.append("[dim]...[/]")
|
|
elif name in disabled_tools:
|
|
colored_names.append(f"[red]{name}[/]")
|
|
else:
|
|
colored_names.append(f"[#FFF8DC]{name}[/]")
|
|
tools_str = ", ".join(colored_names)
|
|
|
|
right_lines.append(f"[dim #B8860B]{toolset}:[/] {tools_str}")
|
|
|
|
if remaining_toolsets > 0:
|
|
right_lines.append(f"[dim #B8860B](and {remaining_toolsets} more toolsets...)[/]")
|
|
|
|
# MCP Servers section (only if configured)
|
|
try:
|
|
from tools.mcp_tool import get_mcp_status
|
|
mcp_status = get_mcp_status()
|
|
except Exception:
|
|
mcp_status = []
|
|
|
|
if mcp_status:
|
|
right_lines.append("")
|
|
right_lines.append("[bold #FFBF00]MCP Servers[/]")
|
|
for srv in mcp_status:
|
|
if srv["connected"]:
|
|
right_lines.append(
|
|
f"[dim #B8860B]{srv['name']}[/] [#FFF8DC]({srv['transport']})[/] "
|
|
f"[dim #B8860B]—[/] [#FFF8DC]{srv['tools']} tool(s)[/]"
|
|
)
|
|
else:
|
|
right_lines.append(
|
|
f"[red]{srv['name']}[/] [dim]({srv['transport']})[/] "
|
|
f"[red]— failed[/]"
|
|
)
|
|
|
|
right_lines.append("")
|
|
right_lines.append("[bold #FFBF00]Available Skills[/]")
|
|
skills_by_category = get_available_skills()
|
|
total_skills = sum(len(s) for s in skills_by_category.values())
|
|
|
|
if skills_by_category:
|
|
for category in sorted(skills_by_category.keys()):
|
|
skill_names = sorted(skills_by_category[category])
|
|
if len(skill_names) > 8:
|
|
display_names = skill_names[:8]
|
|
skills_str = ", ".join(display_names) + f" +{len(skill_names) - 8} more"
|
|
else:
|
|
skills_str = ", ".join(skill_names)
|
|
if len(skills_str) > 50:
|
|
skills_str = skills_str[:47] + "..."
|
|
right_lines.append(f"[dim #B8860B]{category}:[/] [#FFF8DC]{skills_str}[/]")
|
|
else:
|
|
right_lines.append("[dim #B8860B]No skills installed[/]")
|
|
|
|
right_lines.append("")
|
|
mcp_connected = sum(1 for s in mcp_status if s["connected"]) if mcp_status else 0
|
|
summary_parts = [f"{len(tools)} tools", f"{total_skills} skills"]
|
|
if mcp_connected:
|
|
summary_parts.append(f"{mcp_connected} MCP servers")
|
|
summary_parts.append("/help for commands")
|
|
right_lines.append(f"[dim #B8860B]{' · '.join(summary_parts)}[/]")
|
|
|
|
right_content = "\n".join(right_lines)
|
|
layout_table.add_row(left_content, right_content)
|
|
|
|
outer_panel = Panel(
|
|
layout_table,
|
|
title=f"[bold #FFD700]Hermes Agent {VERSION}[/]",
|
|
border_style="#CD7F32",
|
|
padding=(0, 2),
|
|
)
|
|
|
|
console.print()
|
|
console.print(HERMES_AGENT_LOGO)
|
|
console.print()
|
|
console.print(outer_panel)
|