KunN-21 cadef6c4ff fix(rtk): make system prompt injection format-safe and idempotent ...

Caveman/Ponytail injection now matches each target wire format instead of
assuming an OpenAI-shaped body:

- Chat arrays append a text block; Responses arrays append input_text and
  create typed message items
- Claude inserts before the final cache-control block; Gemini preserves the
  snake/camel systemInstruction wrapper
- Kiro updates systemPrompt and its mirrored first-user prefix atomically,
  rolling back if the pair fails to converge
- Format label decides Claude/Gemini before the wire-shape sniff, since their
  bodies also carry messages[]/contents[] and Anthropic rejects a "system"
  role inside messages[]
- Delimiter-aware dedup makes injection exact-idempotent across retries, so
  distinct prompts sharing a long prefix are no longer collapsed
- Every write is fail-open on frozen or proxied bodies

Saver order and X-9Router-Token-Saver: off behavior are unchanged.

Fixes #3202.

2026-08-28 11:47:56 +07:00

12 KiB

Raw Blame History

View Raw