hermes-agent/tools at ebf69d155b6073a67135acdb43c2f995c5f5abd1 - hermes-agent - Hermes Gitea

Timmy_Foundation/hermes-agent

Files

History

Alexander Whitestone ebf69d155b feat: GPU Inference Scheduler — Multi-Model Resource Management

Fixes #645

Queue-based model loading with priority lanes and VRAM budget tracking.
Prevents GPU OOM crashes when multiple projects compete for VRAM.

## Features

### Priority Lanes
- REALTIME (1): LPM, live video, interactive sessions
- INTERACTIVE (2): Playground, chat, user-facing
- BATCH (3): Harvester, overnight jobs, background

### VRAM Management
- Tracks total/used/available VRAM
- Reserves VRAM when job starts
- Releases VRAM when job completes
- CPU fallback when GPU full

### Model Registry
Pre-registered models:
- Video Forge: SD XL (8GB), HeartMuLa (4GB), Wan2.1 (12GB)
- LPM: Video Gen (16GB), A2A (8GB)
- Local: Llama 3 70B (40GB), Llama 3 8B (8GB), MiMo v2 Pro (16GB)
- Playground: SDXL Turbo (6GB)

### Cross-Project Scenarios Handled
1. Video Forge batch + LPM live → LPM gets priority
2. 3 Video Forge jobs → Sequential with shared cache
3. Night harvester + playground → Batch runs on idle cycles

## Files
- tools/gpu_scheduler.py: InferenceScheduler class, CLI interface
- tests/tools/test_gpu_scheduler.py: 19 tests, all passing

## Usage
```python
from tools.gpu_scheduler import InferenceScheduler, Priority

scheduler = InferenceScheduler(vram_budget_mb=49152)  # 48GB
scheduler.submit_job("job-1", "lpm", "llama3_8b", Priority.REALTIME)
job = scheduler.get_next_job()
scheduler.start_job(job)
# ... do inference ...
scheduler.complete_job(job)
```

2026-04-14 21:15:58 -04:00

..

browser_providers

feat: switch managed browser provider from Browserbase to Browser Use (#5750 )

2026-04-07 08:40:22 -04:00

perf(ssh,modal): bulk file sync via tar pipe and tar/base64 archive (#8014 )

2026-04-12 06:18:05 +05:30

refactor(tts): replace NeuTTS optional skill with built-in provider + setup flow

2026-03-17 02:33:12 -07:00

__init__.py

Merge branch 'main' into rewbs/tool-use-charge-to-subscription

2026-03-31 08:48:54 +09:00

ansi_strip.py

fix: strip ANSI at the source — clean terminal output before it reaches the model

2026-03-23 07:43:12 -07:00

approval.py

fix: block agent from self-destructing gateway via terminal (#6666 )

2026-04-14 15:43:31 -07:00

binary_extensions.py

fix(tools): address PR review — remove _extract_raw_output, BudgetConfig everywhere, read_file hardening

2026-04-08 02:24:32 -07:00

browser_camofox_state.py

feat(browser): add persistent Camofox sessions and VNC URL discovery (salvage #4400 ) (#4419 )

2026-04-01 04:18:50 -07:00

browser_camofox.py

fix: remove 115 verified dead code symbols across 46 production files

2026-04-10 03:44:43 -07:00

browser_tool.py

fix(browser): add termux PATH fallbacks

2026-04-14 16:55:55 -07:00

budget_config.py

fix: preserve existing thresholds, remove pre-read byte guard

2026-04-08 02:24:32 -07:00

checkpoint_manager.py

fix: normalize checkpoint manager home-relative paths

2026-04-11 14:50:44 -07:00

clarify_tool.py

refactor: add tool_error/tool_result helpers + read_raw_config, migrate 129 callsites

2026-04-07 13:36:38 -07:00

code_execution_tool.py

fix: remove sandbox language from tool descriptions

2026-04-13 04:23:27 -07:00

credential_files.py

refactor: extract shared helpers to deduplicate repeated code patterns (#7917 )

2026-04-11 13:59:52 -07:00

cronjob_tools.py

refactor: remove dead code — 1,784 lines across 77 files (#9180 )

2026-04-13 16:32:04 -07:00

debug_helpers.py

refactor: codebase-wide lint cleanup — unused imports, dead code, and inefficient patterns (#5821 )

2026-04-07 10:25:31 -07:00

delegate_tool.py

fix: list all available toolsets in delegate_task schema description (#8231 )

2026-04-12 00:54:35 -07:00

env_passthrough.py

refactor: remove dead code — 1,784 lines across 77 files (#9180 )

2026-04-13 16:32:04 -07:00

file_operations.py

feat: improve file search UX — fuzzy @ completions, mtime sorting, better suggestions (#9467 )

2026-04-13 23:54:45 -07:00

file_tools.py

refactor: remove dead code — 1,784 lines across 77 files (#9180 )

2026-04-13 16:32:04 -07:00

fuzzy_match.py

fix(patch): harden V4A patch parser and fuzzy match — 9 correctness bugs

2026-04-10 16:47:44 -07:00

gpu_scheduler.py

feat: GPU Inference Scheduler — Multi-Model Resource Management

2026-04-14 21:15:58 -04:00

homeassistant_tool.py

fix: clean up description escaping, add string-data tests

2026-04-13 04:45:07 -07:00

image_generation_tool.py

refactor: remove dead code — 1,784 lines across 77 files (#9180 )

2026-04-13 16:32:04 -07:00

interrupt.py

fix: scope tool interrupt signal per-thread to prevent cross-session leaks (#7930 )

2026-04-11 14:02:58 -07:00

managed_tool_gateway.py

fix(tools): add debug logging for token refresh and tighten domain check

2026-04-02 12:40:03 +11:00

mcp_oauth.py

fix(approval,mcp): log silent exception handlers, narrow OAuth catches, close server on error

2026-04-10 03:05:04 -07:00

mcp_tool.py

fix(mcp): make server aliases explicit

2026-04-14 17:19:20 -07:00

memory_tool.py

fix: nest msvcrt import inside fcntl except block

2026-04-14 10:18:05 -07:00

mixture_of_agents_tool.py

refactor: remove dead code — 1,784 lines across 77 files (#9180 )

2026-04-13 16:32:04 -07:00

neutts_synth.py

fix(tts): document NeuTTS provider and align install guidance (#1903 )

2026-03-18 02:55:30 -07:00

openrouter_client.py

refactor: route ad-hoc LLM consumers through centralized provider router

2026-03-11 20:02:36 -07:00

osv_check.py

feat: OSV malware check for MCP extension packages (#5305 )

2026-04-05 12:46:07 -07:00

patch_parser.py

fix(patch): harden V4A patch parser and fuzzy match — 9 correctness bugs

2026-04-10 16:47:44 -07:00

path_security.py

refactor: extract shared helpers to deduplicate repeated code patterns (#7917 )

2026-04-11 13:59:52 -07:00

process_registry.py

fix: suppress duplicate completion notifications when agent already consumed output via wait/poll/log (#8228 )

2026-04-12 00:36:22 -07:00

registry.py

fix(mcp): make server aliases explicit

2026-04-14 17:19:20 -07:00

rl_training_tool.py

refactor: codebase-wide lint cleanup — unused imports, dead code, and inefficient patterns (#5821 )

2026-04-07 10:25:31 -07:00

send_message_tool.py

fix: add platform lock, send retry, message splitting, REST one-shot, shared strip_markdown

2026-04-14 00:11:49 -07:00

session_search_tool.py

fix(session_search): improve truncation to center on actual query matches

2026-04-13 04:54:42 -07:00

skill_manager_tool.py

security: supply chain hardening — CI pinning, dep pinning, and code fixes (#9801 )

2026-04-14 14:23:37 -07:00

skills_guard.py

refactor: remove dead code — 1,784 lines across 77 files (#9180 )

2026-04-13 16:32:04 -07:00

skills_hub.py

feat(skills): centralized skills index — eliminate GitHub API calls for search/install

2026-04-12 16:39:04 -07:00

skills_sync.py

fix(skills): read name from SKILL.md frontmatter in skills_sync

2026-04-11 01:21:20 -07:00

skills_tool.py

feat(plugins): namespaced skill registration for plugin skill bundles

2026-04-14 10:42:58 -07:00

terminal_tool.py

refactor: remove dead code — 1,784 lines across 77 files (#9180 )

2026-04-13 16:32:04 -07:00

tirith_security.py

chore: fix 154 f-strings, simplify getattr/URL patterns, remove dead code (#3119 )

2026-03-25 19:47:58 -07:00

todo_tool.py

fix(tools): enforce ID uniqueness in TODO store during replace operations

2026-04-11 16:22:50 -07:00

tool_backend_helpers.py

Merge branch 'main' into rewbs/tool-use-charge-to-subscription

2026-03-31 08:48:54 +09:00

tool_result_storage.py

fix(tools): neutralize shell injection in _write_to_sandbox via path quoting (#7940 )

2026-04-11 14:26:11 -07:00

transcription_tools.py

refactor: remove dead code — 1,784 lines across 77 files (#9180 )

2026-04-13 16:32:04 -07:00

tts_tool.py

feat(tts): add speed support for Edge TTS and OpenAI TTS

2026-04-12 16:46:18 -07:00

url_safety.py

fix: make safe_url_for_log public, add SSRF redirect guards to base.py cache helpers

2026-04-10 05:04:28 -07:00

vision_tools.py

refactor: remove dead code — 1,784 lines across 77 files (#9180 )

2026-04-13 16:32:04 -07:00

voice_mode.py

refactor: remove dead code — 1,784 lines across 77 files (#9180 )

2026-04-13 16:32:04 -07:00

web_tools.py

refactor: remove dead code — 1,784 lines across 77 files (#9180 )

2026-04-13 16:32:04 -07:00

website_policy.py

refactor: codebase-wide lint cleanup — unused imports, dead code, and inefficient patterns (#5821 )

2026-04-07 10:25:31 -07:00