mirror of
https://github.com/modelstudioai/cli.git
synced 2026-09-14 19:49:23 +08:00
lisheng.lisheng
aef6c1accf
Adopt the code-review findings and reconcile every writer with the official
Model Studio docs (with cc-switch / each agent's own docs as secondary refs).
- qwen-code: drop deprecated security.auth.apiKey/baseUrl (keep only
selectedType), restore $version:3, model:{name}; env BAILIAN_API_KEY.
- codex: official env_key="OPENAI_API_KEY" structure (drop requires_openai_auth
/ model_reasoning_effort / disable_response_storage); respect $CODEX_HOME.
- hermes: revert to official flat model.* block; api_mode only for anthropic
endpoints (omitted for OpenAI-compatible).
- opencode: drop setCacheKey; target existing opencode.jsonc when present.
- openclaw: stop hardcoding 1M contextWindow; add optional --context-window;
add agents.defaults.models.
- claude-code: respect $CLAUDE_CONFIG_DIR.
- utils: on parse failure, throw and keep the original file (no silent wipe).
- tests: rewrite writer unit tests + add missing-flag e2e for every required
flag; regenerate skill reference; document `bl config agent` in READMEs.