docs: refresh transcript sanitization mirrors

This commit is contained in:
Peter Steinberger
2026-04-04 21:52:10 +01:00
parent de918c282c
commit 291afbbb95
9 changed files with 28 additions and 15 deletions

View File

@@ -37,10 +37,13 @@ The returned view is intentionally bounded and safety-filtered:
- assistant text is normalized before recall:
- thinking tags are stripped
- `<relevant-memories>` / `<relevant_memories>` scaffolding blocks are stripped
- plain-text tool-call XML payload blocks such as `<tool_call>...</tool_call>` / `<function_calls>...</function_calls>` are stripped
- plain-text tool-call XML payload blocks such as `<tool_call>...</tool_call>`,
`<tool_calls>...</tool_calls>`, and `<function_calls>...</function_calls>`
are stripped, including truncated payloads that never close cleanly
- downgraded tool-call/result scaffolding such as `[Tool Call: ...]`,
`[Tool Result ...]`, and `[Historical context ...]` is stripped
- leaked model control tokens such as `<|assistant|>` / `<...>` are stripped
- leaked model control tokens such as `<|assistant|>`, other ASCII
`<|...|>` tokens, and full-width `<...>` variants are stripped
- malformed MiniMax tool-call XML such as `<invoke ...>` /
`</minimax:tool_call>` is stripped
- credential/token-like text is redacted before it is returned