WeKnora/internal
LuckVd b5c8d90cc2
fix(chat_pipeline): treat non-JSON model refusals as skipped graph extraction (#3606)
* fix(chat_pipeline): treat non-JSON model refusals as skipped graph extraction

When a chunk carries nothing extractable (e.g. a table-of-contents page),
the LLM correctly answers with a prose refusal such as "抱歉…". parseOutput
then fed that prose to json.Unmarshal, failing with a confusing
"invalid character 'æ'" (the first byte of a CJK character), marking the
chunk task GRAPH_EXTRACT_FAILED and letting asynq replay the identical
doomed LLM call up to the retry limit.

Classify responses that contain no JSON structure at all (no '{' or '[')
as errModelDeclined and complete the extraction with an empty graph so the
task succeeds as an explicit skip. Malformed or truncated JSON (structure
present) still fails and retries as before.

Fixes #3600

* fix(chat_pipeline): keep empty model responses retriable in graph extraction

An empty response is usually transient (gateway returning 200 with no
content, a reasoning model spending its whole budget on reasoning,
content filtering), and a retry often succeeds. Only non-empty prose
with no JSON structure is treated as a declined extraction.

* fix(graph): skip prose refusals only in the async chunk task, keep truncation retriable

ParseGraph no longer turns a prose answer into an empty graph. It returns
an error wrapping ErrModelDeclined, and ChunkExtractService.Handle is the
only caller that treats it as a skip (span output skipped=model_declined).
The /initialization "try extract" endpoint and query-side entity extraction
report the refusal as a failure again, so the graph settings form no longer
gets its few-shot examples replaced with an empty result.

Extractor.Extract drops the ErrModelDeclined marker when finish_reason is
"length": prose with no JSON because the output budget ran out is
truncation, and asynq should retry it.

* fix(graph): retry every truncation spelling, not only finish_reason=length

Extract kept a prose answer retriable only when FinishReason was exactly
"length". max_tokens / max_output_tokens (and case/space variants that
IsLengthFinishReason already accepts), a stream that broke before the stop
event ("incomplete") and an adapter that reports no reason were still read
as a refusal, so the async chunk task skipped the chunk for good.

Only a reason that proves the model stopped on its own now counts as a
refusal. Ollama's non-streaming Chat also forwards done_reason, so a
num_predict cut-off is reported as "length" instead of an empty string.

* fix(graph): only treat a response with no JSON anywhere as a refusal

The refusal check looked at the first extracted fence, so a prose fence
followed by a JSON fence was skipped as a refusal instead of failing as a
retriable parse error.

---------

Co-authored-by: LuckVd <LuckVd@users.noreply.github.com>
Co-authored-by: wizardchen <wizardchen@tencent.com>
2026-10-08 14:57:11 +08:00
..
agent fix(kb): let the update API set vlm_config (#3704) 2026-10-08 14:37:23 +08:00
application fix(chat_pipeline): treat non-JSON model refusals as skipped graph extraction (#3606) 2026-10-08 14:57:11 +08:00
assets feat(assets): add ASR test audio file and embed it in the application 2026-04-02 21:27:27 +08:00
browserskill fix(browser): refine connection and preview UI with extension version 2026-09-23 10:57:59 +08:00
common fix(markdown): sanitize invalid UTF-8 and NUL bytes 2026-08-31 12:24:35 +08:00
config feat(auth): 新增仅限邀请注册档位 (#3900) 2026-09-30 13:32:55 +08:00
container fix: use consistent qdrant env settings (#3960) 2026-10-07 23:59:56 +08:00
database revert: take the plugin system back out of main 2026-09-26 14:58:18 +08:00
datasource fix(rss): refresh titles and source links when article text is unchanged (#3824) 2026-10-08 14:02:56 +08:00
embedpolicy fix(embed): enforce host origin allowlists on framed pages 2026-09-14 18:03:57 +08:00
errors feat(knowledge): flag documents that stop making progress (#3557) 2026-09-22 21:34:08 +08:00
event fix(agent): end the turn when the completion cap truncates an answer (#3449) 2026-09-20 13:17:50 +08:00
filetransport refactor(resource-access): unify scoped authorization and transfer recovery (#3097) 2026-09-08 15:36:33 +08:00
handler fix(chat_pipeline): treat non-JSON model refusals as skipped graph extraction (#3606) 2026-10-08 14:57:11 +08:00
im fix(im/wecom): preserve image in mixed messages with text captions (#3901) 2026-10-08 01:25:25 +08:00
infrastructure fix(docparser): 云解析超时改为跟随既有配置,不再硬编码 (#3891) 2026-10-08 14:02:42 +08:00
ipclass fix: align client sessions and integration request handling (#3305) 2026-09-16 16:20:57 +08:00
localsandbox feat(lite): install and run skills on the host (#3661) 2026-09-24 21:30:34 +08:00
logger fix(logger): keep LLM debug records inside their directory 2026-09-25 18:22:14 +08:00
mcp fix(mcp): pass embedded resources in tool results to the agent (#3766) 2026-10-08 01:25:04 +08:00
mcpserver fix(mcp): return accessible image URLs from existing tools (#3650) 2026-09-24 11:56:25 +08:00
middleware fix(middleware): stop buffering whole request bodies in the access log (#3927) 2026-10-08 01:29:05 +08:00
modelcontext fix(agent): 图谱查询的三处截断必须可见,模型不再把子图当全集 (#3885) 2026-10-07 23:59:50 +08:00
models fix(chat_pipeline): treat non-JSON model refusals as skipped graph extraction (#3606) 2026-10-08 14:57:11 +08:00
ratelimit feat(embed): add backend embed channels with auth and rate limiting (#1657) 2026-06-12 23:10:39 +08:00
reranking fix(retrieval): fix recall correctness, score scales, cost and agent tools (#3687) 2026-09-25 10:48:18 +08:00
router fix(frontend): 修复复制模型时模型名称被改写的问题 (#3830) 2026-09-29 19:32:08 +08:00
runtime fix(server): run ResourceCleaner on signal shutdown instead of racing Fatalf exit (#3804) 2026-09-28 23:37:36 +08:00
sandbox fix(sandbox): reclassify exec races with the idle sweep as NotFound so rebinding heals (#3980) 2026-10-08 01:28:53 +08:00
searchutil feat(wiki): 增加跨知识库 Wiki 搜索 POST /wiki-search (#3535) 2026-09-25 22:22:58 +08:00
sourceloc fix(citations): 修复原文定位、高亮范围与 DocReader 启动失败 (#3794) 2026-09-27 20:32:26 +08:00
storageallowlist fix(storage): align default provider fallback with STORAGE_ALLOW_LIST 2026-07-15 11:05:00 +08:00
storageurl fix(mcp): return accessible image URLs from existing tools (#3650) 2026-09-24 11:56:25 +08:00
stream feat(session): in-place rewind with workspace checkpoint reset (#3469) 2026-09-20 21:01:00 +08:00
textconv fix: remove GPL converter and bundle third-party license sources 2026-09-08 15:19:10 +08:00
tracing/langfuse fix(milvus): preserve keyword retrieval scores 2026-09-17 11:59:40 +08:00
types fix(kb): let the update API set vlm_config (#3704) 2026-10-08 14:37:23 +08:00
utils fix(multimodal): bound remote image downloads by the file size limit (#3906) 2026-10-08 13:14:04 +08:00