DhanushSantosh b2e5ff1460 fix: centralize model prefix handling to prevent provider errors ...

Moves prefix stripping from individual providers to AgentService/IdeationService
and adds validation to ensure providers receive bare model IDs. This prevents
bugs like the Codex CLI receiving "codex-gpt-5.1-codex-max" instead of the
expected "gpt-5.1-codex-max".

- Add validateBareModelId() helper with fail-fast validation
- Add originalModel field to ExecuteOptions for logging
- Update all providers to validate model has no prefix
- Centralize prefix stripping in service layer
- Remove redundant prefix stripping from individual providers

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>

2026-01-09 01:40:29 +05:30

..

dependency-resolver

completly remove sandbox related code as the downstream libraries do not work with it on various os

2026-01-07 08:54:14 -05:00

git-utils

refactor: use Vitest projects config instead of deprecated workspace

2026-01-05 14:45:33 +01:00

model-resolver

fix: update model resolver for codex- prefix and fix thinking/reasoning separation

2026-01-09 00:45:31 +05:30

platform

feat: enhance authentication handling and API key validation

2026-01-07 19:26:42 +05:30

prompts

refactor: use Vitest projects config instead of deprecated workspace

2026-01-05 14:45:33 +01:00

types

fix: centralize model prefix handling to prevent provider errors

2026-01-09 01:40:29 +05:30

utils

refactor: use Vitest projects config instead of deprecated workspace

2026-01-05 14:45:33 +01:00

tsconfig.base.json

refactor: Centralize ESM config in tsconfig.base.json

2025-12-21 00:26:26 +01:00