WeKnora/internal/agent
linus-liu-web 436d02fdf3 fix(compaction): 流因取消而关闭时不得当成空摘要成功返回
streamSummary 的 select 里 ctx.Done() 分支与 stream 关闭分支会同时就绪,
select 在就绪分支之间随机选择:已经取消的调用有一半概率走关闭分支返回 nil,
被报成"成功返回空摘要",另一半才返回 context.Canceled。CI 上因此偶发:

--- FAIL: TestSummarizationIsNotRetriedOnceTheTurnIsCancelled (0.00s)
    stream_test.go:122: Error: Should be true
FAIL	github.com/Tencent/WeKnora/internal/agent/compaction

这不只是测试问题。流因取消而关闭被当成成功,会让调用方把中途被截断的摘要
当有效 checkpoint 落盘(成功路径会走到 saveContextCheckpoint),而
validateSummary 只拦得住空摘要和 finish_reason 为 length 的截断。

修复:在流关闭分支返回成功之前先查 ctx.Err()。既纠正语义(取消就是取消,
不是空摘要),也消除两个分支同时就绪时的随机性。streamErr 的优先级仍在
ctx.Err() 之前,因为供应商报的错更具体;ctx 未取消、流自然关闭的正常完成
仍返回内容加 nil,stall 与重试逻辑未动。

回归用例 TestSummarizationIsCancelledWhenTheStreamCloses:假模型同步返回
一个已经关闭的 channel,传入已取消的 ctx,两个分支必然同时就绪。修复前
-count=50 有 20 次 FAIL,修复后 -count=50 全 PASS;既有 flaky 用例
TestSummarizationIsNotRetriedOnceTheTurnIsCancelled -count=100 全 PASS。
2026-09-29 01:30:01 +08:00
..
approval refactor(agent): discover and invoke MCP tools on demand 2026-09-08 12:01:36 +08:00
compaction fix(compaction): 流因取消而关闭时不得当成空摘要成功返回 2026-09-29 01:30:01 +08:00
skills feat(lite): install and run skills on the host (#3661) 2026-09-24 21:30:34 +08:00
token refactor(models): rebuild vendor integration on protocol + catalog + vendor layers (#3470) 2026-09-20 21:28:23 +08:00
tools revert: take the plugin system back out of main 2026-09-26 14:58:18 +08:00
act.go fix(agent): recover tool panics instead of crashing the server 2026-09-25 18:22:14 +08:00
act_order_test.go fix(agent): recover tool panics instead of crashing the server 2026-09-25 18:22:14 +08:00
calibration.go feat(agent): size agent history by the window and calibrate token estimates (#3413) 2026-09-18 22:51:31 +08:00
calibration_test.go feat(agent): size agent history by the window and calibrate token estimates (#3413) 2026-09-18 22:51:31 +08:00
checkpoint.go feat(agent): size agent history by the window and calibrate token estimates (#3413) 2026-09-18 22:51:31 +08:00
const.go fix(models): keep Retry-After on HTTPError and honour it in agent LLM retries 2026-09-29 01:22:15 +08:00
const_test.go fix(browser): support human handoffs and resume interrupted tasks 2026-09-11 23:56:13 +08:00
context_debug.go refactor(models): rebuild vendor integration on protocol + catalog + vendor layers (#3470) 2026-09-20 21:28:23 +08:00
engine.go feat(sandbox): run unpinned Lite sessions on the host OS sandbox (#3549) 2026-09-22 19:35:03 +08:00
engine_image_test.go feat: auto-describe MCP tool result images via VLM 2026-03-25 21:38:15 +08:00
engine_memory_test.go feat(memory): add cross-session long-term memory 2026-08-13 18:00:02 +08:00
engine_test.go fix(llm): treat cut-off streams as broken and tighten LLM retries 2026-09-25 18:22:14 +08:00
finalize.go feat(agent): size agent history by the window and calibrate token estimates (#3413) 2026-09-18 22:51:31 +08:00
grounding_prompt.go fix(agent): search bound knowledge bases before answering, and pass suggested-question origins (#3400) 2026-09-18 17:00:47 +08:00
grounding_prompt_test.go fix(agent): search bound knowledge bases before answering, and pass suggested-question origins (#3400) 2026-09-18 17:00:47 +08:00
knowledge_base_profile_prompt_test.go feat(knowledge): derive knowledge base descriptions from document profiles (#3370) 2026-09-17 22:21:55 +08:00
langfuse_test.go refactor(agent): introduce modelcontext registry and fix handle-codec bugs 2026-07-27 11:05:43 +08:00
length_truncation_test.go fix(agent): end the turn when the completion cap truncates an answer (#3449) 2026-09-20 13:17:50 +08:00
mcp_exposure_test.go fix(mcp): normalize JSON-encoded argument envelopes 2026-09-09 16:11:52 +08:00
mcp_proxy_test.go fix(mcp): normalize JSON-encoded argument envelopes 2026-09-09 16:11:52 +08:00
observe.go refactor(models): rebuild vendor integration on protocol + catalog + vendor layers (#3470) 2026-09-20 21:28:23 +08:00
observe_test.go fix(agent): search bound knowledge bases before answering, and pass suggested-question origins (#3400) 2026-09-18 17:00:47 +08:00
prompt_composition_test.go fix(agent): search bound knowledge bases before answering, and pass suggested-question origins (#3400) 2026-09-18 17:00:47 +08:00
prompts.go feat(sandbox): run unpinned Lite sessions on the host OS sandbox (#3549) 2026-09-22 19:35:03 +08:00
prompts_browser.go fix(browser): align BrowserSkill 0.3.0 and repair task lifecycle 2026-09-17 11:54:12 +08:00
prompts_browser_test.go feat(browser): polish connection settings, open tasks in a new window, and streamline prompts (#3193) 2026-09-11 21:28:58 +08:00
prompts_shell_test.go feat(sandbox): run unpinned Lite sessions on the host OS sandbox (#3549) 2026-09-22 19:35:03 +08:00
prompts_wiki.go fix(wiki): 整页重写被补全预算截断时续写,续写用尽则拒绝写回(长名单 146→119) (#3582) 2026-09-23 12:17:07 +08:00
prompts_wiki_test.go refactor(agent): introduce modelcontext registry and fix handle-codec bugs 2026-07-27 11:05:43 +08:00
retry_delay_test.go fix(models): keep Retry-After on HTTPError and honour it in agent LLM retries 2026-09-29 01:22:15 +08:00
steer.go fix(chat): preserve steering continuity and composer focus 2026-09-09 20:15:23 +08:00
steer_test.go fix(chat): preserve steering continuity and composer focus 2026-09-09 20:15:23 +08:00
terminal_event_test.go fix(agent): stop emitting terminal answer events for retryable empty stops 2026-09-14 21:02:15 +08:00
think.go fix(models): keep Retry-After on HTTPError and honour it in agent LLM retries 2026-09-29 01:22:15 +08:00
tool_images.go fix(browser): complete task cancellation, screenshots, and result display (#3206) 2026-09-12 09:32:26 +08:00
tool_images_test.go refactor(models): separate provider definitions, model catalogs, and runtime configuration (#3589) 2026-09-23 14:20:08 +08:00
turn_usage_test.go feat(agent): size agent history by the window and calibrate token estimates (#3413) 2026-09-18 22:51:31 +08:00