Victor Hong eb3dff8458 fix: Add JSON output flag to gemini CLI configuration ...

The gemini CLI was returning plain text instead of JSON, causing clink to fail with:
'Failed to decode Gemini CLI JSON output: Expecting value: line 1 column 1 (char 0)'

Root cause: gemini.json was missing the '-o json' flag in additional_args.

This fix adds '-o json' to ensure JSON output format, aligning with the codex pattern (which uses --json).

Tested with gemini CLI v0.8.2

2025-10-14 18:28:16 +11:00

..

cli_clients

fix: Add JSON output flag to gemini CLI configuration

2025-10-14 18:28:16 +11:00

__init__.py

Complete PR review feedback implementation with clean importlib.resources approach

2025-08-10 22:13:25 +07:00

azure_models.json

feat: all native providers now read from catalog files like OpenRouter / Custom configs. Allows for greater control over the capabilities

2025-10-07 12:17:47 +04:00

custom_models.json

feat!: breaking change - OpenRouter models are now read from conf/openrouter_models.json while Custom / Self-hosted models are read from conf/custom_models.json

2025-10-04 21:10:56 +04:00

dial_models.json

refactor: moved registries into a separate module and code cleanup

2025-10-07 12:59:09 +04:00

gemini_models.json

feat!: Full code can now be generated by an external model and shared with the AI tool (Claude Code / Codex etc)!

2025-10-07 18:49:13 +04:00

openai_models.json

feat!: Full code can now be generated by an external model and shared with the AI tool (Claude Code / Codex etc)!

2025-10-07 18:49:13 +04:00

openrouter_models.json

feat!: Full code can now be generated by an external model and shared with the AI tool (Claude Code / Codex etc)!

2025-10-07 18:49:13 +04:00

xai_models.json

feat: all native providers now read from catalog files like OpenRouter / Custom configs. Allows for greater control over the capabilities

2025-10-07 12:17:47 +04:00