Skip to content
Python

Merge pull request #261 from Tencent-Hunyuan/feat/sdk-multilingual-prompts

feitianxiang75ac1b01f2ff
diff --cc CHANGELOG.md
index b59854a,48f0d1e..274d417
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@@ -4,10 -4,37 +4,39 @@@ Hy Memory and MemHub are versioned and
## Unreleased
+ - Hy Memory: LLM prompts now ship in 11 languages: `en`, `zh-Hans`,
+ `zh-Hant`, `ja`, `es`, `de`, `pt`, `fr`, `ko`, `ru` and `id`. They live in
+ one registry, `hy_memory/prompts/`, with one module per language. Call
+ sites use `get_prompt(name, language)`, so a new language only needs a new
+ module. The registry covers chat extraction (system prompt, basic_info,
+ intentions, few-shot including Example 11), the no-intention variant,
+ reconcile and its search-query prompt, the working/coding extractor, both
+ coding reconcilers and the chain summary, the episode and topic summaries,
+ System 2 evolve, and the user name line. The English and Simplified Chinese
+ strings are unchanged byte for byte, and a test pins them. The old names
+ (`prompts_zh.*_ZH`, `extractor.EXTRACT_SYSTEM_PROMPT`, ...) still import.
+ The nine new languages are machine translations, and native-speaker review
+ is recommended.
+ - Hy Memory: new optional `language` to choose the prompt language
+ explicitly. Set it on `MemoryConfig.language` (env `MEMORY_LANGUAGE`) for
+ a client default, or per call on `add` / `async_add`, `add_extracted`,
+ `finalize_session`, `evolve` and `sweep`. A per-call value overrides the
+ config. The value goes through every LLM call of the request: extract and
+ basic profile, reconcile, the coding path, the summaries and System 2.
+ Aliases: `zh`, `zh-CN` → `zh-Hans`; `zh-TW`, `zh-HK` → `zh-Hant`; `pt-BR` →
+ `pt`. An unknown code raises `ValueError` listing the supported codes, and
+ the HTTP server returns 400. With an explicit language, memories are
+ written in that language even when the conversation uses another one.
+ Without a language, the existing zh/en auto-detection runs unchanged and
+ memories keep the source language. `search` has no `language`: its judge
+ and rewrite prompts are English-only and keep the query's language.
+ - Hy Memory: the HTTP server accepts `language` on `/api/v1/add` and
+ `/api/v1/add_extracted`.
+
## Hy Memory 2.0.10 — 2026-11-01
+- Published
+ [`hy-memory==2.0.10`](https://pypi.org/project/hy-memory/2.0.10/).
- New `hy_memory.reembed` module for switching the embedding
model. Writers must be paused for the whole run. Nothing is derived from
the provider or endpoint: source and target are named explicitly, and the