Experience reconcile no longer falls back to ADD-all, and fact reconcile no
longer inserts without superseding, when the model call fails, returns empty
content, or returns a reply that is not a JSON object with an ops list. The
write returns success=false, agent_error_code=RECONCILE_FAILED and the
cause in reconcile_error_code (LLM_UNAVAILABLE / EMPTY_RESPONSE /
JSON_PARSE_FAILED), the same as chat.
Each reconciler is split into plan() (retrieve + model decision, no store)
and apply() (store). CodingWriter plans both layers before applying either,
so a decision failure in either layer stores no experience or fact and
supersedes no older fact. reconcile() still runs plan + apply.
An experience reply of {"ops": []} is a valid "no changes" decision and
stores nothing. A non-empty ops list with no recognizable op is a parse
failure. A fact reply of {"ops": []} inserts without superseding.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Reconcile (add / add_extracted): when the reconcile model call fails,
returns an empty 200 reply or an unparseable reply, or reconcile raises
before anything is stored, the write no longer falls back to adding every
extracted memory as-is with success=true. The ADD-all fallback and its
degraded flags are removed. The write returns success=false,
agent_error_code=RECONCILE_FAILED and the cause in reconcile_error_code
(LLM_UNAVAILABLE / EMPTY_RESPONSE / JSON_PARSE_FAILED /
RECONCILE_EXCEPTION). Nothing new is stored, the episode counter does not
advance, and add rolls back its L1 raw (retry_safe=true), so a re-run with
a new request_id is clean. Only a literal [] still means "no changes".
RECONCILE_ENABLED=false keeps writing directly.
Working / coding path: an extraction model failure (LLM_ERROR,
EMPTY_RESPONSE, JSON_PARSE_FAILED) and an experience or fact embedding
failure (EMBEDDING_FAILED) now return success=false instead of success
with 0 ops or a node without a vector. Embeddings are computed before the
SQLite row is written and before an older fact is superseded. A failed
write does not append its trace or record chain rounds. A model that
answers with nothing to remember is still a success.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Move every LLM prompt that had a zh variant into one registry,
hy_memory/prompts/, with one module per language (en, zh-Hans, zh-Hant,
ja, es, de, pt, fr, ko, ru, id). Call sites look prompts up with
get_prompt(name, language), so a new language needs only a new module.
The en and zh-Hans strings are moved verbatim, a test pins their sha256,
and the old names (prompts_zh.*_ZH, extractor.EXTRACT_SYSTEM_PROMPT, ...)
still import.
Add an optional language: MemoryConfig.language (env MEMORY_LANGUAGE)
as the client default, plus a per-call language= on add / async_add,
add_extracted, finalize_session, evolve and sweep. It goes through
extract and basic profile, reconcile and search query, the coding
extractor and both coding reconcilers with the chain summary, the
episode and topic summaries, and System 2. Codes are validated, with
aliases (zh, zh-CN, zh-TW, zh-HK, pt-BR); an unknown code raises
ValueError. With an explicit language, memories are written in that
language. Without one, the zh/en auto-detection is unchanged. The
server accepts language on /add and /add_extracted.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
client.add passed memory_at only to the chat path; the productivity writer
dropped it and coding_memory_meta / working_fact had no column for it, so
every experience had only its write time and MemHub showed it as 时间未知.
Both tables gain a nullable memory_at column (epoch seconds), added to
existing coding/working databases on open. The writer stamps it on drafts
and new facts, defaulting to the request time as chat does; an UPDATE keeps
the later of the stored and incoming times. list_memories (coding, working,
all), get and search return memory_at in chat's format.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
alvinfeiandClaude Opus 5.5
