mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-04-28 06:51:16 +08:00
Add a claude code-like CLI
- Introduced `cli-config.yaml.example` to provide a template for configuring the CLI behavior, including model settings, terminal tool configurations, agent behavior, and toolsets. - Created `cli.py` for an interactive terminal interface, allowing users to start the Hermes Agent with various options and toolsets. - Added `hermes` launcher script for convenient CLI access. - Updated `model_tools.py` to support quiet mode for suppressing output during tool initialization and execution. - Enhanced logging in various tools to respect quiet mode, improving user experience by reducing unnecessary output. - Added `prompt_toolkit` to `requirements.txt` for improved CLI interaction capabilities. - Created `TODO.md` for future improvements and enhancements to the Hermes Agent framework.
This commit is contained in:
teknium
@@ -99,7 +99,13 @@ DEBUG_DATA = {
|
||||
# Create logs directory if debug mode is enabled
|
||||
if DEBUG_MODE:
|
||||
DEBUG_LOG_PATH.mkdir(exist_ok=True)
|
||||
print(f"🐛 Debug mode enabled - Session ID: {DEBUG_SESSION_ID}")
|
||||
_verbose_print(f"🐛 Debug mode enabled - Session ID: {DEBUG_SESSION_ID}")
|
||||
|
||||
|
||||
def _verbose_print(*args, **kwargs):
|
||||
"""Print only if not in quiet mode (HERMES_QUIET not set)."""
|
||||
if not os.getenv("HERMES_QUIET"):
|
||||
print(*args, **kwargs)
|
||||
|
||||
|
||||
def _log_debug_call(tool_name: str, call_data: Dict[str, Any]) -> None:
|
||||
@@ -140,7 +146,7 @@ def _save_debug_log() -> None:
|
||||
with open(debug_filepath, 'w', encoding='utf-8') as f:
|
||||
json.dump(DEBUG_DATA, f, indent=2, ensure_ascii=False)
|
||||
|
||||
print(f"🐛 Debug log saved: {debug_filepath}")
|
||||
_verbose_print(f"🐛 Debug log saved: {debug_filepath}")
|
||||
|
||||
except Exception as e:
|
||||
print(f"❌ Error saving debug log: {str(e)}")
|
||||
@@ -185,12 +191,12 @@ async def process_content_with_llm(
|
||||
# Refuse if content is absurdly large
|
||||
if content_len > MAX_CONTENT_SIZE:
|
||||
size_mb = content_len / 1_000_000
|
||||
print(f"🚫 Content too large ({size_mb:.1f}MB > 2MB limit). Refusing to process.")
|
||||
_verbose_print(f"🚫 Content too large ({size_mb:.1f}MB > 2MB limit). Refusing to process.")
|
||||
return f"[Content too large to process: {size_mb:.1f}MB. Try using web_crawl with specific extraction instructions, or search for a more focused source.]"
|
||||
|
||||
# Skip processing if content is too short
|
||||
if content_len < min_length:
|
||||
print(f"📏 Content too short ({content_len} < {min_length} chars), skipping LLM processing")
|
||||
_verbose_print(f"📏 Content too short ({content_len} < {min_length} chars), skipping LLM processing")
|
||||
return None
|
||||
|
||||
# Create context information
|
||||
@@ -203,13 +209,13 @@ async def process_content_with_llm(
|
||||
|
||||
# Check if we need chunked processing
|
||||
if content_len > CHUNK_THRESHOLD:
|
||||
print(f"📦 Content large ({content_len:,} chars). Using chunked processing...")
|
||||
_verbose_print(f"📦 Content large ({content_len:,} chars). Using chunked processing...")
|
||||
return await _process_large_content_chunked(
|
||||
content, context_str, model, CHUNK_SIZE, MAX_OUTPUT_SIZE
|
||||
)
|
||||
|
||||
# Standard single-pass processing for normal content
|
||||
print(f"🧠 Processing content with LLM ({content_len} characters)")
|
||||
_verbose_print(f"🧠 Processing content with LLM ({content_len} characters)")
|
||||
|
||||
processed_content = await _call_summarizer_llm(content, context_str, model)
|
||||
|
||||
@@ -221,7 +227,7 @@ async def process_content_with_llm(
|
||||
# Log compression metrics
|
||||
processed_length = len(processed_content)
|
||||
compression_ratio = processed_length / content_len if content_len > 0 else 1.0
|
||||
print(f"✅ Content processed: {content_len} → {processed_length} chars ({compression_ratio:.1%})")
|
||||
_verbose_print(f"✅ Content processed: {content_len} → {processed_length} chars ({compression_ratio:.1%})")
|
||||
|
||||
return processed_content
|
||||
|
||||
@@ -318,8 +324,8 @@ Create a markdown summary that captures all key information in a well-organized,
|
||||
except Exception as api_error:
|
||||
last_error = api_error
|
||||
if attempt < max_retries - 1:
|
||||
print(f"⚠️ LLM API call failed (attempt {attempt + 1}/{max_retries}): {str(api_error)[:100]}")
|
||||
print(f" Retrying in {retry_delay}s...")
|
||||
_verbose_print(f"⚠️ LLM API call failed (attempt {attempt + 1}/{max_retries}): {str(api_error)[:100]}")
|
||||
_verbose_print(f" Retrying in {retry_delay}s...")
|
||||
await asyncio.sleep(retry_delay)
|
||||
retry_delay = min(retry_delay * 2, 60)
|
||||
else:
|
||||
@@ -355,7 +361,7 @@ async def _process_large_content_chunked(
|
||||
chunk = content[i:i + chunk_size]
|
||||
chunks.append(chunk)
|
||||
|
||||
print(f" 📦 Split into {len(chunks)} chunks of ~{chunk_size:,} chars each")
|
||||
_verbose_print(f" 📦 Split into {len(chunks)} chunks of ~{chunk_size:,} chars each")
|
||||
|
||||
# Summarize each chunk in parallel
|
||||
async def summarize_chunk(chunk_idx: int, chunk_content: str) -> tuple[int, Optional[str]]:
|
||||
@@ -371,10 +377,10 @@ async def _process_large_content_chunked(
|
||||
chunk_info=chunk_info
|
||||
)
|
||||
if summary:
|
||||
print(f" ✅ Chunk {chunk_idx + 1}/{len(chunks)} summarized: {len(chunk_content):,} → {len(summary):,} chars")
|
||||
_verbose_print(f" ✅ Chunk {chunk_idx + 1}/{len(chunks)} summarized: {len(chunk_content):,} → {len(summary):,} chars")
|
||||
return chunk_idx, summary
|
||||
except Exception as e:
|
||||
print(f" ⚠️ Chunk {chunk_idx + 1}/{len(chunks)} failed: {str(e)[:50]}")
|
||||
_verbose_print(f" ⚠️ Chunk {chunk_idx + 1}/{len(chunks)} failed: {str(e)[:50]}")
|
||||
return chunk_idx, None
|
||||
|
||||
# Run all chunk summarizations in parallel
|
||||
@@ -391,7 +397,7 @@ async def _process_large_content_chunked(
|
||||
print(f" ❌ All chunk summarizations failed")
|
||||
return "[Failed to process large content: all chunk summarizations failed]"
|
||||
|
||||
print(f" 📊 Got {len(summaries)}/{len(chunks)} chunk summaries")
|
||||
_verbose_print(f" 📊 Got {len(summaries)}/{len(chunks)} chunk summaries")
|
||||
|
||||
# If only one chunk succeeded, just return it (with cap)
|
||||
if len(summaries) == 1:
|
||||
@@ -401,7 +407,7 @@ async def _process_large_content_chunked(
|
||||
return result
|
||||
|
||||
# Synthesize the summaries into a final summary
|
||||
print(f" 🔗 Synthesizing {len(summaries)} summaries...")
|
||||
_verbose_print(f" 🔗 Synthesizing {len(summaries)} summaries...")
|
||||
|
||||
combined_summaries = "\n\n---\n\n".join(summaries)
|
||||
|
||||
@@ -443,11 +449,11 @@ Create a single, unified markdown summary."""
|
||||
final_len = len(final_summary)
|
||||
compression = final_len / original_len if original_len > 0 else 1.0
|
||||
|
||||
print(f" ✅ Synthesis complete: {original_len:,} → {final_len:,} chars ({compression:.2%})")
|
||||
_verbose_print(f" ✅ Synthesis complete: {original_len:,} → {final_len:,} chars ({compression:.2%})")
|
||||
return final_summary
|
||||
|
||||
except Exception as e:
|
||||
print(f" ⚠️ Synthesis failed: {str(e)[:100]}")
|
||||
_verbose_print(f" ⚠️ Synthesis failed: {str(e)[:100]}")
|
||||
# Fall back to concatenated summaries with truncation
|
||||
fallback = "\n\n".join(summaries)
|
||||
if len(fallback) > max_output_size:
|
||||
@@ -534,7 +540,8 @@ def web_search_tool(query: str, limit: int = 5) -> str:
|
||||
}
|
||||
|
||||
try:
|
||||
print(f"🔍 Searching the web for: '{query}' (limit: {limit})")
|
||||
if not os.getenv("HERMES_QUIET"):
|
||||
_verbose_print(f"🔍 Searching the web for: '{query}' (limit: {limit})")
|
||||
|
||||
# Use Firecrawl's v2 search functionality WITHOUT scraping
|
||||
# We only want search result metadata, not scraped content
|
||||
@@ -574,7 +581,8 @@ def web_search_tool(query: str, limit: int = 5) -> str:
|
||||
web_results = response['web']
|
||||
|
||||
results_count = len(web_results)
|
||||
print(f"✅ Found {results_count} search results")
|
||||
if not os.getenv("HERMES_QUIET"):
|
||||
_verbose_print(f"✅ Found {results_count} search results")
|
||||
|
||||
# Build response with just search metadata (URLs, titles, descriptions)
|
||||
response_data = {
|
||||
@@ -654,7 +662,7 @@ async def web_extract_tool(
|
||||
}
|
||||
|
||||
try:
|
||||
print(f"📄 Extracting content from {len(urls)} URL(s)")
|
||||
_verbose_print(f"📄 Extracting content from {len(urls)} URL(s)")
|
||||
|
||||
# Determine requested formats for Firecrawl v2
|
||||
formats: List[str] = []
|
||||
@@ -672,7 +680,7 @@ async def web_extract_tool(
|
||||
|
||||
for url in urls:
|
||||
try:
|
||||
print(f" 📄 Scraping: {url}")
|
||||
_verbose_print(f" 📄 Scraping: {url}")
|
||||
scrape_result = _get_firecrawl_client().scrape(
|
||||
url=url,
|
||||
formats=formats
|
||||
@@ -748,14 +756,14 @@ async def web_extract_tool(
|
||||
response = {"results": results}
|
||||
|
||||
pages_extracted = len(response.get('results', []))
|
||||
print(f"✅ Extracted content from {pages_extracted} pages")
|
||||
_verbose_print(f"✅ Extracted content from {pages_extracted} pages")
|
||||
|
||||
debug_call_data["pages_extracted"] = pages_extracted
|
||||
debug_call_data["original_response_size"] = len(json.dumps(response))
|
||||
|
||||
# Process each result with LLM if enabled
|
||||
if use_llm_processing and os.getenv("OPENROUTER_API_KEY"):
|
||||
print("🧠 Processing extracted content with LLM (parallel)...")
|
||||
_verbose_print("🧠 Processing extracted content with LLM (parallel)...")
|
||||
debug_call_data["processing_applied"].append("llm_processing")
|
||||
|
||||
# Prepare tasks for parallel processing
|
||||
@@ -813,12 +821,12 @@ async def web_extract_tool(
|
||||
if status == "processed":
|
||||
debug_call_data["compression_metrics"].append(metrics)
|
||||
debug_call_data["pages_processed_with_llm"] += 1
|
||||
print(f" 📝 {url} (processed)")
|
||||
_verbose_print(f" 📝 {url} (processed)")
|
||||
elif status == "too_short":
|
||||
debug_call_data["compression_metrics"].append(metrics)
|
||||
print(f" 📝 {url} (no processing - content too short)")
|
||||
_verbose_print(f" 📝 {url} (no processing - content too short)")
|
||||
else:
|
||||
print(f" ⚠️ {url} (no content to process)")
|
||||
_verbose_print(f" ⚠️ {url} (no content to process)")
|
||||
else:
|
||||
if use_llm_processing and not os.getenv("OPENROUTER_API_KEY"):
|
||||
print("⚠️ LLM processing requested but OPENROUTER_API_KEY not set, returning raw content")
|
||||
@@ -828,7 +836,7 @@ async def web_extract_tool(
|
||||
for result in response.get('results', []):
|
||||
url = result.get('url', 'Unknown URL')
|
||||
content_length = len(result.get('raw_content', ''))
|
||||
print(f" 📝 {url} ({content_length} characters)")
|
||||
_verbose_print(f" 📝 {url} ({content_length} characters)")
|
||||
|
||||
# Trim output to minimal fields per entry: title, content, error
|
||||
trimmed_results = [
|
||||
@@ -923,10 +931,10 @@ async def web_crawl_tool(
|
||||
# Ensure URL has protocol
|
||||
if not url.startswith(('http://', 'https://')):
|
||||
url = f'https://{url}'
|
||||
print(f" 📝 Added https:// prefix to URL: {url}")
|
||||
_verbose_print(f" 📝 Added https:// prefix to URL: {url}")
|
||||
|
||||
instructions_text = f" with instructions: '{instructions}'" if instructions else ""
|
||||
print(f"🕷️ Crawling {url}{instructions_text}")
|
||||
_verbose_print(f"🕷️ Crawling {url}{instructions_text}")
|
||||
|
||||
# Use Firecrawl's v2 crawl functionality
|
||||
# Docs: https://docs.firecrawl.dev/features/crawl
|
||||
@@ -943,7 +951,7 @@ async def web_crawl_tool(
|
||||
# Note: The 'prompt' parameter is not documented for crawl
|
||||
# Instructions are typically used with the Extract endpoint, not Crawl
|
||||
if instructions:
|
||||
print(f" ℹ️ Note: Instructions parameter ignored (not supported in crawl API)")
|
||||
_verbose_print(f" ℹ️ Note: Instructions parameter ignored (not supported in crawl API)")
|
||||
|
||||
# Use the crawl method which waits for completion automatically
|
||||
try:
|
||||
@@ -963,23 +971,23 @@ async def web_crawl_tool(
|
||||
# The crawl_result is a CrawlJob object with a 'data' attribute containing list of Document objects
|
||||
if hasattr(crawl_result, 'data'):
|
||||
data_list = crawl_result.data if crawl_result.data else []
|
||||
print(f" 📊 Status: {getattr(crawl_result, 'status', 'unknown')}")
|
||||
print(f" 📄 Retrieved {len(data_list)} pages")
|
||||
_verbose_print(f" 📊 Status: {getattr(crawl_result, 'status', 'unknown')}")
|
||||
_verbose_print(f" 📄 Retrieved {len(data_list)} pages")
|
||||
|
||||
# Debug: Check other attributes if no data
|
||||
if not data_list:
|
||||
print(f" 🔍 Debug - CrawlJob attributes: {[attr for attr in dir(crawl_result) if not attr.startswith('_')]}")
|
||||
print(f" 🔍 Debug - Status: {getattr(crawl_result, 'status', 'N/A')}")
|
||||
print(f" 🔍 Debug - Total: {getattr(crawl_result, 'total', 'N/A')}")
|
||||
print(f" 🔍 Debug - Completed: {getattr(crawl_result, 'completed', 'N/A')}")
|
||||
_verbose_print(f" 🔍 Debug - CrawlJob attributes: {[attr for attr in dir(crawl_result) if not attr.startswith('_')]}")
|
||||
_verbose_print(f" 🔍 Debug - Status: {getattr(crawl_result, 'status', 'N/A')}")
|
||||
_verbose_print(f" 🔍 Debug - Total: {getattr(crawl_result, 'total', 'N/A')}")
|
||||
_verbose_print(f" 🔍 Debug - Completed: {getattr(crawl_result, 'completed', 'N/A')}")
|
||||
|
||||
elif isinstance(crawl_result, dict) and 'data' in crawl_result:
|
||||
data_list = crawl_result.get("data", [])
|
||||
else:
|
||||
print(" ⚠️ Unexpected crawl result type")
|
||||
print(f" 🔍 Debug - Result type: {type(crawl_result)}")
|
||||
_verbose_print(f" 🔍 Debug - Result type: {type(crawl_result)}")
|
||||
if hasattr(crawl_result, '__dict__'):
|
||||
print(f" 🔍 Debug - Result attributes: {list(crawl_result.__dict__.keys())}")
|
||||
_verbose_print(f" 🔍 Debug - Result attributes: {list(crawl_result.__dict__.keys())}")
|
||||
|
||||
for item in data_list:
|
||||
# Process each crawled page - properly handle object serialization
|
||||
@@ -1044,14 +1052,14 @@ async def web_crawl_tool(
|
||||
response = {"results": pages}
|
||||
|
||||
pages_crawled = len(response.get('results', []))
|
||||
print(f"✅ Crawled {pages_crawled} pages")
|
||||
_verbose_print(f"✅ Crawled {pages_crawled} pages")
|
||||
|
||||
debug_call_data["pages_crawled"] = pages_crawled
|
||||
debug_call_data["original_response_size"] = len(json.dumps(response))
|
||||
|
||||
# Process each result with LLM if enabled
|
||||
if use_llm_processing and os.getenv("OPENROUTER_API_KEY"):
|
||||
print("🧠 Processing crawled content with LLM (parallel)...")
|
||||
_verbose_print("🧠 Processing crawled content with LLM (parallel)...")
|
||||
debug_call_data["processing_applied"].append("llm_processing")
|
||||
|
||||
# Prepare tasks for parallel processing
|
||||
@@ -1109,12 +1117,12 @@ async def web_crawl_tool(
|
||||
if status == "processed":
|
||||
debug_call_data["compression_metrics"].append(metrics)
|
||||
debug_call_data["pages_processed_with_llm"] += 1
|
||||
print(f" 🌐 {page_url} (processed)")
|
||||
_verbose_print(f" 🌐 {page_url} (processed)")
|
||||
elif status == "too_short":
|
||||
debug_call_data["compression_metrics"].append(metrics)
|
||||
print(f" 🌐 {page_url} (no processing - content too short)")
|
||||
_verbose_print(f" 🌐 {page_url} (no processing - content too short)")
|
||||
else:
|
||||
print(f" ⚠️ {page_url} (no content to process)")
|
||||
_verbose_print(f" ⚠️ {page_url} (no content to process)")
|
||||
else:
|
||||
if use_llm_processing and not os.getenv("OPENROUTER_API_KEY"):
|
||||
print("⚠️ LLM processing requested but OPENROUTER_API_KEY not set, returning raw content")
|
||||
@@ -1124,7 +1132,7 @@ async def web_crawl_tool(
|
||||
for result in response.get('results', []):
|
||||
page_url = result.get('url', 'Unknown URL')
|
||||
content_length = len(result.get('content', ''))
|
||||
print(f" 🌐 {page_url} ({content_length} characters)")
|
||||
_verbose_print(f" 🌐 {page_url} ({content_length} characters)")
|
||||
|
||||
# Trim output to minimal fields per entry: title, content, error
|
||||
trimmed_results = [
|
||||
@@ -1246,7 +1254,7 @@ if __name__ == "__main__":
|
||||
|
||||
# Show debug mode status
|
||||
if DEBUG_MODE:
|
||||
print(f"🐛 Debug mode ENABLED - Session ID: {DEBUG_SESSION_ID}")
|
||||
_verbose_print(f"🐛 Debug mode ENABLED - Session ID: {DEBUG_SESSION_ID}")
|
||||
print(f" Debug logs will be saved to: ./logs/web_tools_debug_{DEBUG_SESSION_ID}.json")
|
||||
else:
|
||||
print("🐛 Debug mode disabled (set WEB_TOOLS_DEBUG=true to enable)")
|
||||
|
||||
Reference in New Issue
Block a user