hermes-agent/tests
teknium1 77da3bbc95 fix: use correct role for summary message in context compressor
The summary message was always injected as 'user' role, which causes
consecutive user messages when the last preserved head message is also
'user'. Some APIs reject this (400 error), and it produces malformed
training data.

Fix: check the role of the last head message and pick the opposite role
for the summary — 'user' after assistant/tool, 'assistant' after user.

Based on PR #328 by johnh4098. Closes #328.
2026-03-08 23:09:04 -07:00
..
agent fix: use correct role for summary message in context compressor 2026-03-08 23:09:04 -07:00
cron Merge PR #309: fix(timezone): timezone-aware now() for prompt, cron, and execute_code 2026-03-07 00:04:41 -08:00
fakes test: add HA integration tests with fake in-process server 2026-02-28 14:28:04 +03:00
gateway fix: unify gateway session hygiene with agent compression config 2026-03-08 21:30:48 -07:00
hermes_cli Merge pull request #732 from NousResearch/hermes/hermes-2cb83eed 2026-03-08 20:10:32 -07:00
honcho_integration Merge PR #193: add unit tests for 5 security/logic-critical modules (batch 4) 2026-03-04 19:35:01 -08:00
integration chore: remove all NOUS_API_KEY references 2026-03-08 17:45:38 -07:00
tools feat: browser console/errors tool, annotated screenshots, auto-recording, and dogfood QA skill 2026-03-08 21:28:12 -07:00
__init__.py A bit of restructuring for simplicity and organization 2025-10-01 23:29:25 +00:00
conftest.py fix(tests): isolate HERMES_HOME in tests and adjust log directory for debug session 2026-03-02 04:34:21 -08:00
test_413_compression.py fix: preflight context compression + error handler ordering for model switches 2026-03-04 14:42:41 -08:00
test_api_key_providers.py fix: add Kimi Code API support (api.kimi.com/coding/v1) 2026-03-07 21:00:12 -05:00
test_atomic_json_write.py refactor: extract atomic_json_write helper, add 24 checkpoint tests 2026-03-06 05:50:12 -08:00
test_auth_codex_provider.py refactor(auth): transition Codex OAuth tokens to Hermes auth store 2026-03-01 19:59:24 -08:00
test_auth_nous_provider.py Fix nous refresh token rotation failure in case where api key mint/retrieval fails 2026-03-02 17:18:15 +11:00
test_auxiliary_config_bridge.py fix: harden auxiliary model config — gateway bridge, vision safety, tests 2026-03-08 18:06:47 -07:00
test_batch_runner_checkpoint.py refactor: extract atomic_json_write helper, add 24 checkpoint tests 2026-03-06 05:50:12 -08:00
test_cli_init.py chore: remove dead module stubs from test_cli_init.py 2026-03-08 05:35:02 -07:00
test_cli_model_command.py fix: improve /model user feedback + update docs 2026-03-08 06:13:12 -07:00
test_cli_provider_resolution.py fix: trust user-selected models with OpenAI Codex provider 2026-03-08 18:29:09 -07:00
test_codex_execution_paths.py feat: simple fallback model for provider resilience 2026-03-08 20:22:33 -07:00
test_codex_models.py Merge pull request #735 from NousResearch/hermes/hermes-f8d56335 2026-03-08 18:30:27 -07:00
test_external_credential_detection.py refactor(auth): transition Codex OAuth tokens to Hermes auth store 2026-03-01 19:59:24 -08:00
test_fallback_model.py refactor: unified OAuth/API-key credential resolution for fallback 2026-03-08 21:44:48 -07:00
test_flush_memories_codex.py refactor(cli): Finalize OpenAI Codex Integration with OAuth 2026-02-28 21:47:51 -08:00
test_hermes_state.py fix: add title validation — sanitize, length limit, control char stripping 2026-03-08 15:54:51 -07:00
test_honcho_client_config.py fix(honcho): auto-enable when API key is present 2026-03-01 03:12:37 -05:00
test_insights.py fix: deep review — prefix matching, tool_calls extraction, query perf, serialization 2026-03-06 14:50:57 -08:00
test_model_tools.py test: strengthen assertions across 3 more test files (batch 2) 2026-03-05 18:46:30 -08:00
test_provider_parity.py feat: default reasoning effort from xhigh to medium 2026-03-07 10:14:19 -08:00
test_resume_display.py feat: display previous messages when resuming a session in CLI 2026-03-08 17:45:45 -07:00
test_run_agent.py fix: allow Anthropic API URLs as custom OpenAI-compatible endpoints 2026-03-07 23:36:35 -08:00
test_run_agent_codex_responses.py refactor(cli): Finalize OpenAI Codex Integration with OAuth 2026-02-28 21:47:51 -08:00
test_runtime_provider_resolution.py fix: custom endpoint no longer leaks OPENROUTER_API_KEY (#560) 2026-03-06 17:16:14 -08:00
test_timezone.py fix(timezone): add timezone-aware clock across agent, cron, and execute_code 2026-03-03 18:23:40 +05:30
test_toolset_distributions.py test: add unit tests for 8 modules (batch 2) 2026-02-26 13:54:20 +03:00
test_toolsets.py test: add unit tests for 8 untested modules 2026-02-26 13:27:58 +03:00
test_trajectory_compressor.py test: add 25 unit tests for trajectory_compressor 2026-02-28 21:28:28 +03:00
test_worktree.py fix: wire worktree flag into hermes CLI entry point + docs + tests 2026-03-07 21:05:40 -08:00