Commit Graph

335 Commits

Author SHA1 Message Date
yyh c56d9e3f69
Merge remote-tracking branch 'origin/main' into deploy/dev 2026-01-09 19:41:17 +08:00
wangxiaolei 0711dd4159
feat: enhance start node object value check (#30732) 2026-01-09 16:13:17 +08:00
QuantumGhost ae0a26f5b6
revert: "fix: fix assign value stand as default (#30651)" (#30717)
The original fix seems correct on its own. However, for chatflows with multiple answer nodes, the `message_replace` command only preserves the output of the last executed answer node.
2026-01-09 16:08:24 +08:00
Yansong Zhang c3d0c80ca1 Merge branch 'feat/credit-pool' into deploy/dev 2026-01-08 11:03:21 +08:00
-LAN- 7ccf858ce6
fix(workflow): pass correct user_from/invoke_from into graph init (#30637) 2026-01-07 21:47:23 +08:00
Novice eec57e84e4
Merge branch 'main' into feat/agent-node-v2 2026-01-07 17:34:23 +08:00
wangxiaolei 187bfafe8b
fix: fix assign value stand as default (#30651)
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2026-01-07 14:54:11 +08:00
-LAN- 55de731f9c
refactor(api): clarify published RAG pipeline invoke naming (#30644) 2026-01-06 23:48:06 +09:00
Novice cef7fd484b
chore: add trace metadata and streaming icon 2026-01-06 16:30:33 +08:00
-LAN- d12b91a01a
refactor(api): inject sessionmaker into conversation variable updater (#30609) 2026-01-06 14:52:59 +08:00
-LAN- d6e9c3310f
feat: Add conversation variable persistence layer (#30531) 2026-01-06 14:05:33 +08:00
-LAN- 6f8bd58e19
feat(graph-engine): make layer runtime state non-null and bound early (#30552)
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2026-01-05 16:43:42 +08:00
-LAN- a99ac3fe0d
refactor(models): Add mapped type hints to MessageAnnotation (#27751) 2026-01-05 15:50:03 +08:00
Novice dc8a618b6a
feat: add think start end tag 2026-01-04 11:09:43 +08:00
Novice f3e7fea628
feat: add tool call time 2026-01-04 10:29:02 +08:00
Novice ccabdbc83b
Merge branch 'main' into feat/agent-node-v2 2025-12-30 10:20:42 +08:00
Shemol d9cecabe93
fix: release graph_runtime_state reference to prevent memory leak under high load (#30236)
Signed-off-by: SherlockShemol <shemol@163.com>
2025-12-29 10:35:47 +08:00
Novice f55faae31b
chore: strip reasoning from chatflow answers and persist generation details 2025-12-25 13:59:38 +08:00
Novice 7fc25cafb2
feat: basic app add thought field 2025-12-25 10:28:21 +08:00
lif 542eb04ad8
fix: preserve empty list for FILE_LIST type in base_app_generator (#29618)
Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>
2025-12-22 21:32:07 +08:00
wangxiaolei e6545f2727
perf: decrease db query (#29837)
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2025-12-18 15:35:52 +08:00
wangxiaolei dd237f129d
fix: fix json object validate (#29840) 2025-12-18 14:46:00 +08:00
Novice 047ea8c143
chore: improve type checking 2025-12-18 10:09:31 +08:00
Novice d3486cab31
refactor(llm node): tool call tool result entity 2025-12-17 10:30:21 +08:00
Novice d223fee9b9
Merge branch 'main' into feat/agent-node-v2 2025-12-15 15:26:48 +08:00
Novice 9ce48b4dc4
fix: llm generation variable 2025-12-12 11:08:49 +08:00
-LAN- 2e1efd62e1
revert: "fix(ops): add streaming metrics and LLM span for agent-chat traces" (#29469) 2025-12-11 12:53:37 +08:00
Novice 2d2ce5df85
feat: generation stream output. 2025-12-09 16:22:17 +08:00
Jyong 9affc546c6
Feat/support multimodal embedding (#29115)
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2025-12-09 14:41:46 +08:00
Novice 2b23c43434
feat: add agent package 2025-12-09 11:36:47 +08:00
heyszt 10b59cd6ba
add service layer OTel Span (#28582)
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2025-12-05 21:58:32 +08:00
fang luping a849411978
fix: treat empty default values for optional file inputs as unset (#28948)
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2025-12-05 11:16:18 +08:00
wangxiaolei 102ee7ae13
perf: optimize generate conversation name (#29131)
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2025-12-05 10:32:53 +08:00
wangxiaolei cc6c59b27a
fix: fix db session already begin (#29160)
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2025-12-05 09:39:39 +08:00
wangxiaolei 725d6b52a7
feat: start node support json schema (#29053) 2025-12-05 01:22:10 +09:00
wangxiaolei e904c65a9d
perf: decrease heavy db operation (#29125) 2025-12-04 16:09:47 +08:00
Yunlu Wen 03357ff1ec
fix: catch error in response converter (#29056)
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2025-12-04 11:25:16 +08:00
wangxiaolei e8f93380d1
Fix validation (#28985)
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2025-12-02 10:25:52 +08:00
wangxiaolei d162f7e5ef
feat(api): automatically `NODE_TYPE_CLASSES_MAPPING` generation from node class definitions (#28525) 2025-12-01 14:14:19 +08:00
wangxiaolei 1b733abe82
feat: creates logs immediately when workflows start (not at completion) (#28701) 2025-11-27 15:22:33 +08:00
XlKsyt 1e23957657
fix(ops): add streaming metrics and LLM span for agent-chat traces (#28320)
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>
2025-11-26 22:45:20 +08:00
QuantumGhost 1c1f124891
Enhanced GraphEngine Pause Handling (#28196)
This commit: 

1. Convert `pause_reason` to `pause_reasons` in `GraphExecution` and relevant classes. Change the field from a scalar value to a list that can contain multiple `PauseReason` objects, ensuring all pause events are properly captured.
2. Introduce a new `WorkflowPauseReason` model to record reasons associated with a specific `WorkflowPause`.

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: -LAN- <laipz8200@outlook.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2025-11-26 19:59:34 +08:00
Xiu-Lan abc13ef762
Feat/web workflow improvements (#27981)
Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>
Co-authored-by: johnny0120 <johnny0120@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Wood <tuiskuwood@outlook.com>
2025-11-25 19:54:40 +08:00
Chen Jiaju 3841e8578f
fix: use default values for optional workflow input variables (#28546) (#28527)
Co-authored-by: Claude <noreply@anthropic.com>
2025-11-24 10:08:26 +08:00
Asuka Minato a6c6bcf95c
more typed orm (#28507) 2025-11-21 21:45:51 +08:00
Asuka Minato 237bb4595b
more typed orm (#28494)
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2025-11-21 16:42:27 +09:00
Maries 012877d8d4
fix: address user input preparation in workflow app generator (#28410)
Co-authored-by: lyzno1 <92089059+lyzno1@users.noreply.github.com>
2025-11-20 02:09:40 +08:00
Yeuoly b76e17b25d
feat: introduce trigger functionality (#27644)
Signed-off-by: lyzno1 <yuanyouhuilyz@gmail.com>
Co-authored-by: Stream <Stream_2@qq.com>
Co-authored-by: lyzno1 <92089059+lyzno1@users.noreply.github.com>
Co-authored-by: zhsama <torvalds@linux.do>
Co-authored-by: Harry <xh001x@hotmail.com>
Co-authored-by: lyzno1 <yuanyouhuilyz@gmail.com>
Co-authored-by: yessenia <yessenia.contact@gmail.com>
Co-authored-by: hjlarry <hjlarry@163.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
Co-authored-by: WTW0313 <twwu@dify.ai>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2025-11-12 17:59:37 +08:00
QuantumGhost fd255e81e1
feat(api): Introduce `WorkflowResumptionContext` for pause state management (#28122)
Certain metadata (including but not limited to `InvokeFrom`, `call_depth`, and `streaming`)  is required when resuming a paused workflow. However, these fields are not part of `GraphRuntimeState` and were not saved in the previous
 implementation of  `PauseStatePersistenceLayer`.

This commit addresses this limitation by introducing a `WorkflowResumptionContext` model that wraps both the `*GenerateEntity` and `GraphRuntimeState`. This approach provides:

- A structured container for all necessary resumption data
- Better separation of concerns between execution state and persistence
- Enhanced extensibility for future metadata additions
- Clearer naming that distinguishes from `GraphRuntimeState`

The `WorkflowResumptionContext` model makes extending the pause state easier while maintaining backward compatibility and proper version management for the entire execution state ecosystem.

Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2025-11-12 17:00:02 +08:00
hj24 37903722fe
refactor: implement tenant self queue for rag tasks (#27559)
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
Co-authored-by: -LAN- <laipz8200@outlook.com>
2025-11-06 21:25:50 +08:00