Mario Zechner 7364696ae6 fix(coding-agent): prefer provider/model split over gateway model id matching ...

When resolving --model zai/glm-5, the resolver now correctly interprets
'zai' as the provider and 'glm-5' as the model id, rather than matching
a vercel-ai-gateway model whose id is literally 'zai/glm-5'.

If the provider/model split fails to find a match, falls back to raw id
matching to still support OpenRouter-style ids like 'openai/gpt-4o:extended'.

2026-02-22 14:40:36 +01:00

..

cli

fix(coding-agent): make resolveCliModel sync, update docs and changelog

2026-02-12 19:04:51 +01:00

core

fix(coding-agent): prefer provider/model split over gateway model id matching

2026-02-22 14:40:36 +01:00

modes

feat: add configurable transport and codex websocket session caching

2026-02-13 23:41:49 +01:00

utils

fix(coding-agent): tighten git source parsing and local path normalization (fixes #1426)

2026-02-12 21:28:06 +01:00

cli.ts

Set coding agent CLI process title (#742)

2026-01-15 13:14:14 +01:00

config.ts

chore(coding-agent): update share viewer url

2026-02-03 22:49:01 +01:00

index.ts

refactor(coding-agent): move auth storage to backend abstraction

2026-02-17 19:57:21 +01:00

main.ts

refactor(coding-agent): move auth storage to backend abstraction

2026-02-17 19:57:21 +01:00

migrations.ts

chore: remove deprecation comment from getToolsDir, add changelog entry for #470

2026-01-05 20:26:48 +01:00