Harry
e9be6bf2ab
feat: add AWS Code Interpreter sandbox provider and update sandbox type
2026-03-10 17:12:15 +08:00
Harry
a8074f4f4a
feat: add DB inline content cache for app asset draft files
...
Introduce app_asset_contents table as a read-through cache over S3 for
text-like asset files (e.g. .md skill documents). This eliminates N
individual S3 fetches during SkillBuilder builds — bulk_load pulls all
content in a single SQL query with S3 fallback on miss.
Key components:
- CachedContentAccessor: DB-first read / dual-write / S3 fallback
- AssetContentService: static DB operations (get, get_many, upsert, delete)
- should_mirror(): single source of truth for extension-based policy
- Alembic migration for app_asset_contents table
Modified callers:
- SkillBuilder uses accessor.bulk_load() instead of per-node S3 reads
- AppAssetService.get/update_file_content route through accessor
- delete_node cleans both DB cache and S3
- draft_app_assets_initializer uses should_mirror() instead of hardcoded .md
2026-03-10 17:12:14 +08:00
Harry
53f76a20c2
refactor: redesign skill compilation and document assembly process
2026-03-10 17:12:14 +08:00
322d3cd555
fix: nested spans and traces; ( #33049 )
...
Co-authored-by: aadereiko <[email protected] >
Co-authored-by: Boris Feld <[email protected] >
Co-authored-by: Claude Opus 4.6 <[email protected] >
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
Co-authored-by: Crazywoola <[email protected] >
2026-03-10 15:45:44 +08:00
wangxiaolei and GitHub
db627e75f6
fix: fix request.metadata_model_config param check ( #33189 )
2026-03-10 15:09:35 +08:00
b9d05d3456
refactor: tool node decouple db ( #33166 )
...
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2026-03-10 01:47:15 +08:00
bbfa28e8a7
refactor: file saver decouple db engine and ssrf proxy ( #33076 )
...
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2026-03-09 16:09:44 +08:00
非法操作 and GitHub
654e41d47f
fix: workflow_as_tool not work with json input ( #32554 )
2026-03-09 13:54:54 +08:00
wangxiaolei and GitHub
46098b2be6
refactor: use thread.Timer instead of time.sleep ( #33121 )
2026-03-09 09:38:16 +08:00
dc2a53d834
feat: add files to message end pr32019 ( #32242 )
...
Co-authored-by: fatelei <[email protected] >
Co-authored-by: angel.k <[email protected] >
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
Co-authored-by: Copilot <[email protected] >
2026-03-07 20:01:12 +08:00
Novice
e0794020f7
feat: extend NodeRunStreamChunkEvent with additional model metadata fields
2026-03-06 17:21:55 +08:00
d01acfc490
fix(api): fix the issue that workflow_runs.started_at is overwritten while resuming ( #32851 )
...
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2026-03-06 15:41:30 +08:00
ad81513b6a
fix: show citations in advanced chat apps ( #32985 )
...
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2026-03-06 09:56:14 +08:00
f751864ab3
fix(api): return inserted ids from Chroma and Clickzetta add_texts ( #33065 )
...
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2026-03-06 09:49:53 +08:00
741d48560d
refactor(api): add TypedDict definitions to models/model.py ( #32925 )
...
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2026-03-06 08:42:54 +09:00
Lovish Arora and GitHub
ed0b27e4d6
chore(api): update Python type-checker versions ( #33056 )
2026-03-06 06:26:28 +09:00
99 and GitHub
7432b58f82
refactor(dify_graph): introduce run_context and delegate child engine creation ( #32964 )
2026-03-05 14:31:28 +08:00
Novice
1cb5ee918f
feat: enhance model event handling with new identity and metrics fields
2026-03-05 14:08:37 +08:00
wangxiaolei and GitHub
882b4c9ef6
refactor: document extract node decouple ssrf_proxy ( #32949 )
2026-03-04 16:01:43 +08:00
wangxiaolei and GitHub
e14b09d4db
refactor: human input node decouple db ( #32900 )
2026-03-04 13:18:32 +08:00
2b47db0462
fix(api): resolve OpenTelemetry histogram type mismatch ( #32771 )
...
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2026-03-04 00:01:16 +09:00
Stream and GitHub
14755d0474
fix: pass parameters correctly for LLMNode.invoke_llm ( #32902 )
2026-03-03 16:32:00 +08:00
99 and GitHub
c8688ec371
refactor(dify_graph): unify invoke and user enums source in workflow ( #32873 )
2026-03-03 15:05:20 +08:00
wangxiaolei and GitHub
1b2234a19f
refactor: TemplateTransformNode decouple code executor ( #32879 )
2026-03-03 13:36:17 +08:00
-LAN- and GitHub
4fd6b52808
refactor(api): move model_runtime into dify_graph ( #32858 )
2026-03-02 20:15:32 +08:00
-LAN- and GitHub
c917838f9c
refactor: move workflow package to dify_graph ( #32844 )
2026-03-02 18:42:30 +08:00
wangxiaolei and GitHub
707bf20c29
refactor: knowledge index node decouples business logic ( #32274 )
2026-03-02 17:54:33 +08:00
Br1an and GitHub
68647391e7
fix(api): add return type annotation to filter_none_values() ( #32774 )
2026-03-02 17:51:21 +09:00
wangxiaolei and GitHub
5c7a293ba7
feat: ensure document id is not missing ( #32765 )
2026-03-02 16:28:31 +08:00
9ddbc1c0fb
fix: map all NodeType values to span kinds in Arize Phoenix tracing ( #32059 )
...
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
Co-authored-by: Crazywoola <[email protected] >
2026-03-02 14:54:26 +08:00
cc127f5b62
fix: fix chat assistant response mode blocking is not work ( #32394 )
...
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2026-03-02 14:05:04 +08:00
baeea77c5b
fix: typo in WebScraper plugin description: "Scrapper" → "Scraper" ( #32790 )
...
Co-authored-by: copilot-swe-agent[bot] <[email protected] >
Co-authored-by: crazywoola <[email protected] >
2026-03-02 10:10:28 +08:00
wangxiaolei and GitHub
9da98e6c6c
fix: fix import error ( #32800 )
2026-03-02 08:59:53 +08:00
99 and GitHub
a01de98721
refactor(workflow): decouple start node external dependencies ( #32793 )
2026-03-02 02:01:41 +08:00
17c1538e03
refactor(workflow): move PromptMessageMemory to model_runtime.memory ( #32796 )
...
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2026-03-02 01:58:02 +08:00
-LAN- and GitHub
69b3e94630
refactor: inject workflow node memory via protocol ( #32784 )
2026-03-02 01:55:49 +08:00
-LAN- and GitHub
ef2b5d6107
refactor(api): move llm quota deduction to app graph layer ( #32786 )
2026-03-01 23:25:36 +08:00
-LAN- and GitHub
ffe77fecdf
revert(graph-engine): rollback stop-event unification ( #32789 )
2026-03-01 19:43:05 +08:00
盐粒 Yanli and GitHub
bc6fd0b5dd
chore: remove ty from backend type-check pipeline ( #32782 )
2026-03-01 19:10:24 +08:00
00e52796e6
refactor(workflow): remove code node helper imports ( #32759 )
...
Co-authored-by: -LAN- <[email protected] >
2026-03-01 16:31:45 +08:00
Br1an and GitHub
cfdf16c49e
fix(api): resolve type errors in BaseTraceInstance and OpsTraceManager ( #32773 )
2026-03-01 17:14:37 +09:00
Br1an and GitHub
d4c508cf8e
fix(api): add explicit return type annotations to clean() methods ( #32772 )
2026-03-01 17:09:43 +09:00
99 and GitHub
9e9e617e09
fix(workflow): decouple http request node external dependencies ( #32762 )
2026-03-01 15:42:57 +08:00
a7789f2c91
fix: some Qwen3 models only support streaming output. ( #32766 )
...
Co-authored-by: Copilot <[email protected] >
2026-03-01 15:42:44 +08:00
FFXN and GitHub
de4dac89ae
fix: Fixed the adaptation issue of response formats for different mod… ( #32326 )
2026-03-01 10:23:17 +08:00
c034eb036c
refactor: inject memory interface into LLMNode ( #32754 )
...
Signed-off-by: -LAN- <[email protected] >
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2026-03-01 04:05:18 +08:00
-LAN- and GitHub
1f0fca89a8
refactor(workflow): move variables package into core.workflow ( #32750 )
2026-03-01 03:15:09 +08:00
-LAN- and GitHub
962df17a15
refactor: consolidate LLM runtime model state on ModelInstance ( #32746 )
...
Signed-off-by: -LAN- <[email protected] >
2026-03-01 02:29:32 +08:00
Harry
a0d1816a6e
feat: add mergeable skill bundles with incremental compilation
...
Refactor skill compilation around mergeable bundle patches so dynamic skill updates no longer require full rebuilds. Keep dependency closures accurate by recomputing affected nodes from direct dependency data.
2026-02-28 14:35:29 +08:00
Tyson Cung and GitHub
91dfdd87e3
fix: replace unreachable yield expression with yield from () ( #32727 )
2026-02-28 15:27:32 +09:00