ccs/lib at 0060c77c257a64c57f4c704d2f32af415434022f - ccs

mirror of https://github.com/tiennm99/ccs.git synced 2026-07-29 14:20:50 +00:00

Files

T

Brian Le 0060c77c25 fix(hooks): handle thinking blocks in image analyzer response parsing

When models have thinking enabled (e.g. codex with thinking: auto), the
API returns content as [{ type: 'thinking', thinking: '...' }, { type:
'text', text: '...' }]. The hook reads content[0].text which is
undefined for thinking blocks, causing 'No text content in response'
errors that block the Read tool (exit 2).

Also fix cross-provider model fallback: getModelsToTry() unconditionally
appends DEFAULT_MODEL (gemini-2.5-flash) as retry, which 502s on
non-gemini provider routes (e.g. codex). Only use DEFAULT_MODEL when no
provider-specific model is configured.

Fixes: content[0].text -> content.find(b => b.type === 'text')
Fixes: cross-provider retry causing 'unknown provider' 502
Ref: #511

2026-03-04 00:29:17 -05:00

hooks

fix(hooks): handle thinking blocks in image analyzer response parsing

2026-03-04 00:29:17 -05:00

prompts

feat(hooks): add image/PDF analysis via CLIProxy transformer

2026-02-03 20:34:05 -05:00

ccs

feat: implement bootstrap conversion and installer updates (Phase 1-3)

2025-11-27 10:24:37 -05:00

ccs.ps1

feat: implement bootstrap conversion and installer updates (Phase 1-3)