fbarrca_obsidian-inlineAI/src
Felix Isaac Lim 3abc20fe6e fix: edge cases — port clash, 403/429 errors, reasoning-only, model reset, token warning
- pre-check port 1455 before OAuth flow to catch clashes early
- 403: friendly message suggesting gpt-5.4-mini fallback
- 429: "subscription limit reached" instead of raw error
- add response.output_text.done SSE path for reasoning-only responses
- reset model to gpt-5.4-mini when switching to Codex provider
- 10s notice on session expiry prompting user to re-sign-in in settings
- warn user tokens stored in plaintext data.json when signed in

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-23 06:33:24 +08:00
..
modules [fix] Fomatting of exports 2025-09-19 17:27:31 +02:00
api.ts style: run prettier to fix format check 2026-05-23 06:30:12 +08:00
codex-auth.ts fix: edge cases — port clash, 403/429 errors, reasoning-only, model reset, token warning 2026-05-23 06:33:24 +08:00
codex-client.ts fix: edge cases — port clash, 403/429 errors, reasoning-only, model reset, token warning 2026-05-23 06:33:24 +08:00
default_prompts.ts Reformat the code with the new prettier config 2025-09-12 18:47:27 +02:00
main.ts Reformat the code with the new prettier config 2025-09-12 18:47:27 +02:00
settings.ts fix: edge cases — port clash, 403/429 errors, reasoning-only, model reset, token warning 2026-05-23 06:33:24 +08:00