hermes-agent/tests/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 test: add unit tests for 8 modules (batch 2) 2026-02-26 13:54:20 +03:00
test_auxiliary_client.py perf(ttft): salvage easy-win startup optimizations from #3346 (#3395) 2026-03-27 07:49:44 -07:00
test_context_compressor.py fix(compression): restore sane defaults and cap summary at 12K tokens 2026-03-24 18:48:47 -07:00
test_display_emoji.py feat(tools): centralize tool emoji metadata in registry + skin integration 2026-03-15 20:21:21 -07:00
test_model_metadata.py feat: overhaul context length detection with models.dev and provider-aware resolution (#2158) 2026-03-20 06:04:33 -07:00
test_models_dev.py feat: overhaul context length detection with models.dev and provider-aware resolution (#2158) 2026-03-20 06:04:33 -07:00
test_prompt_builder.py feat: GPT tool-use steering + strip budget warnings from history 2026-03-27 21:02:23 -07:00
test_prompt_caching.py fix(prompt-caching): skip top-level cache_control on role:tool for OpenRouter 2026-03-21 16:54:43 -07:00
test_redact.py fix(tests): resolve all consistently failing tests 2026-03-22 05:58:26 -07:00
test_skill_commands.py perf(ttft): cache skills prompt with shared skill_utils module (salvage #3366) (#3421) 2026-03-27 10:54:02 -07:00
test_smart_model_routing.py fix: hermes update causes dual gateways on macOS (launchd) (#1567) 2026-03-16 12:36:29 -07:00
test_subagent_progress.py fix(display): fix subagent progress tree-view visual nits 2026-02-28 23:29:49 -08:00
test_title_generator.py feat: auto-generate session titles after first exchange 2026-03-17 04:14:40 -07:00
test_usage_pricing.py feat: use endpoint metadata for custom model context and pricing (#1906) 2026-03-18 03:04:07 -07:00