oterm/tests/unit
Pescador Barquero a93d1c659e
Rely on pydantic to determine DeepSeek thinking capability
The reasoner model is no longer served by DeepSeek and with it goes the
need to string matching check. Now Pydantic properly determines that all
V4 models have thinking capability.

Update capabilities unit test to check for DeepSeek's current V4 model.
2026-08-01 08:43:07 -05:00
..
__init__.py Add unit-tier tests for agent, store, config, utils, providers 2026-04-24 20:06:56 +03:00
test_agent.py Resolve selected capability names into agent capabilities 2026-07-24 20:01:22 +03:00
test_capabilities.py Rely on pydantic to determine DeepSeek thinking capability 2026-08-01 08:43:07 -05:00
test_cli.py Qualify MCP tool names by server 2026-07-31 15:46:30 +03:00
test_config.py Clean up stale config fields, CSS classes, and command descriptions 2026-04-25 00:06:16 +03:00
test_provider_settings.py Handle additional deprecations, rename appropriately providers according to the new pydantic-ai names 2026-05-22 11:35:11 +03:00
test_providers.py Handle additional deprecations, rename appropriately providers according to the new pydantic-ai names 2026-05-22 11:35:11 +03:00
test_providers_ollama.py Sort imports in chat_edit; cover blank-line skip in Modelfile parser 2026-06-30 11:13:22 +03:00
test_store.py Pre-select the provider of the last created chat 2026-07-31 17:12:47 +03:00
test_store_upgrades.py Qualify MCP tool names by server 2026-07-31 15:46:30 +03:00
test_types.py Yield (thinking, text) tuples from stream_agent 2026-04-24 22:11:03 +03:00
test_utils.py fix: add android support (#288) 2026-05-02 06:06:16 -04:00