hermes-agent/agent
Teknium 4a33705838
feat: GPT tool-use steering + strip budget warnings from history
Two changes to improve tool reliability, especially for OpenAI GPT models:

1. GPT tool-use enforcement prompt: Adds GPT_TOOL_USE_GUIDANCE to the
   system prompt when the model name contains 'gpt' and tools are loaded.
   This addresses a known behavioral pattern where GPT models describe
   intended actions ('I will run the tests') instead of actually making
   tool calls. Inspired by similar steering in OpenCode (beast.txt) and
   Cline (GPT-5.1 variant).

2. Budget warning history stripping: Budget pressure warnings injected by
   _get_budget_warning() into tool results are now stripped when
   conversation history is replayed via run_conversation(). Previously,
   these turn-scoped signals persisted across turns, causing models to
   avoid tool calls in all subsequent messages after any turn that hit
   the 70-90% iteration threshold.
2026-03-27 21:02:23 -07:00
..
__init__.py Refactor Terminal and AIAgent cleanup 2026-02-21 22:31:43 -08:00
anthropic_adapter.py fix(anthropic): use model-native output limits instead of hardcoded 16K (#3426) 2026-03-27 13:02:52 -07:00
auxiliary_client.py fix: guard aux LLM calls against None content + reasoning fallback + retry (salvage #3389) (#3449) 2026-03-27 15:28:19 -07:00
context_compressor.py chore: remove ~100 unused imports across 55 files (#3016) 2026-03-25 15:02:03 -07:00
context_references.py fix: add timeout to subprocess calls in context_references (#3469) 2026-03-27 17:51:14 -07:00
copilot_acp_client.py fix(acp): preserve leading whitespace in streaming chunks 2026-03-20 09:38:13 -07:00
display.py fix(gateway): silence background agent terminal output (#3297) 2026-03-26 17:40:31 -07:00
insights.py chore: fix 154 f-strings, simplify getattr/URL patterns, remove dead code (#3119) 2026-03-25 19:47:58 -07:00
model_metadata.py feat: curate HF model picker with OpenRouter analogues (#3440) 2026-03-27 13:54:46 -07:00
models_dev.py fix: 6 bugs in model metadata, reasoning detection, and delegate tool 2026-03-20 08:52:37 -07:00
prompt_builder.py feat: GPT tool-use steering + strip budget warnings from history 2026-03-27 21:02:23 -07:00
prompt_caching.py fix(prompt-caching): skip top-level cache_control on role:tool for OpenRouter 2026-03-21 16:54:43 -07:00
redact.py fix(redact): safely handle non-string inputs 2026-03-21 16:55:02 -07:00
skill_commands.py fix: disabled skills respected across banner, system prompt, slash commands, and skill_view (#1897) 2026-03-18 03:17:37 -07:00
skill_utils.py perf(ttft): cache skills prompt with shared skill_utils module (salvage #3366) (#3421) 2026-03-27 10:54:02 -07:00
smart_model_routing.py feat: integrate GitHub Copilot providers across Hermes 2026-03-17 23:40:22 -07:00
title_generator.py feat: auto-generate session titles after first exchange 2026-03-17 04:14:40 -07:00
trajectory.py Refactor Terminal and AIAgent cleanup 2026-02-21 22:31:43 -08:00
usage_pricing.py fix: status bar shows 26K instead of 260K for token counts with trailing zeros (#3024) 2026-03-25 12:45:58 -07:00