Yijia-Xiao e848b5e812 fix(llm): gate MiniMax reasoning_split by model capability (#826) ...

MinimaxChatOpenAI unconditionally set reasoning_split=True, but the
kwarg is only valid on M2.x reasoning models. The openai SDK's strict
kwarg validation raised TypeError for Coding Plan and any other non-
reasoning MiniMax model.

Adds requires_reasoning_split to ModelCapabilities, gates the payload
injection on it, and only sets True for _MINIMAX_THINKING (M2.x exact
IDs and the ^MiniMax-M\d forward-compat pattern). Same shape as the
existing supports_tool_choice gate.

Regression tests cover both halves: M2.x models still receive the flag,
non-reasoning MiniMax models do not.

2026-05-17 07:49:42 +00:00

..

__init__.py

feat: add analysis-only crypto asset mode

2026-04-18 20:42:11 +08:00

conftest.py

feat(llm): GLM dual-region split + catalog refresh

2026-05-11 04:19:50 +00:00

test_analyst_execution.py

fix(graph): integrate #487 + #567 — sentiment label, route, propagate asset_type

2026-05-17 07:25:59 +00:00

test_api_key_env.py

feat(cli): detect missing provider API keys and persist to .env

2026-05-11 06:12:34 +00:00

test_capabilities.py

fix(llm): gate MiniMax reasoning_split by model capability (#826)

2026-05-17 07:49:42 +00:00

test_checkpoint_resume.py

feat: add LangGraph checkpoint resume for crash recovery (#594)

2026-04-25 08:47:15 +00:00

test_crypto_asset_mode.py

feat: add analysis-only crypto asset mode

2026-04-18 20:42:11 +08:00

test_dataflows_config.py

fix: bundle config/recursion/missing-key fixes

2026-05-11 02:30:24 +00:00

test_deepseek_reasoning.py

fix(llm): structured output for DeepSeek V4 and reasoner

2026-05-11 01:12:28 +00:00

test_env_overrides.py

feat(config): TRADINGAGENTS_* env-var overlay for DEFAULT_CONFIG

2026-05-11 06:12:31 +00:00

test_google_api_key.py

test: lazy-load LLM provider clients and add API-key fixtures so the test suite runs cleanly without credentials (#588)

2026-04-25 07:41:36 +00:00

test_memory_log.py

feat(reflection): configurable alpha benchmark for non-US tickers

2026-05-11 09:14:28 +00:00

test_minimax.py

fix(llm): gate MiniMax reasoning_split by model capability (#826)

2026-05-17 07:49:42 +00:00

test_model_validation.py

test: lazy-load LLM provider clients and add API-key fixtures so the test suite runs cleanly without credentials (#588)

2026-04-25 07:41:36 +00:00

test_ollama_base_url.py

feat(ollama): allow Custom model ID in the CLI dropdown

2026-05-11 09:03:06 +00:00

test_safe_ticker_component.py

fix(security): validate ticker before using as path component (#618)

2026-05-01 18:56:36 +00:00

test_signal_processing.py

feat: structured-output Portfolio Manager + 5-tier rating consistency (#434)

2026-04-25 19:57:26 +00:00

test_structured_agents.py

feat: structured-output Trader and Research Manager (#434, finishes the trio)

2026-04-25 20:27:23 +00:00

test_ticker_symbol_handling.py

test: lazy-load LLM provider clients and add API-key fixtures so the test suite runs cleanly without credentials (#588)

2026-04-25 07:41:36 +00:00