Compare commits

...
Author SHA1 Message Date
twwu 15c1b63474 feat(tools): support tool-generated A2UI parts
Stream, validate, persist, and render constrained UI parts from tools, including the current-time component. Preserve markdown following think blocks as normal answer content.
2026-07-24 10:46:12 +08:00
14c50a9f09 feat(web): locate workflow nodes by node_id in the workflow editor (#38187)
Co-authored-by: Crazywoola <100913391+crazywoola@users.noreply.github.com>
2026-07-24 02:16:41 +00:00
Stephen ZhouGitHubautofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
ba5b26be03 feat(dataset): add website crawl preview (#39324)
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2026-07-24 02:10:39 +00:00
samzongGitHubautofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
922ed4d67d feat(oauth): expose stable account id on provider account endpoint (#39470)
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2026-07-24 02:09:48 +00:00
zyssyz123andGitHub a8a83a357c fix(agent): show workflow node runs in logs (#39471) 2026-07-24 01:59:57 +00:00
Stephen ZhouGitHubautofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
302b50c4fb feat(dataset): add source connections (#39319)
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2026-07-23 13:54:12 +00:00
Byron.wangandGitHub 43254c1ded chore: avoid duplicate token counting during dataset indexing (#39466) 2026-07-23 10:56:03 +00:00
JoelandGitHub 2beafdc457 fix: chat not pass doc if not support vision (#39461) 2026-07-23 10:01:43 +00:00
zyssyz123andGitHub 0198e32447 fix(agent): start new Preview conversations without an ID (#39463) 2026-07-23 09:53:08 +00:00
samzongandGitHub b8f91d0e61 fix(web): echo OAuth state on authorize redirect (#39459)
Signed-off-by: samzong <samzong.lu@gmail.com>
2026-07-23 09:30:52 +00:00
非法操作andGitHub 452dff5c37 fix(api): prevent identity logging deadlock (#39449) 2026-07-23 09:08:04 +00:00
Xiyuan ChenGitHubautofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>yyhyyh
b56ac4af4d feat: gate agent management behind the agent.manage permission (#39330)
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
Co-authored-by: yyh <yuanyouhuilyz@gmail.com>
Co-authored-by: yyh <92089059+lyzno1@users.noreply.github.com>
2026-07-23 07:34:07 +00:00
Stephen ZhouGitHubautofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2a0661a769 feat(dataset): add New Knowledge creation flow (#39315)
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2026-07-23 07:25:14 +00:00
euxGitHubautofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
00fe96325d fix(web): support TTS playback in Safari and Firefox (#39444)
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2026-07-23 06:36:52 +00:00
非法操作andGitHub a3c18c561e chore: improve lambda plugin runtime error display (#39437) 2026-07-23 06:05:14 +00:00
1835e8ef31 fix: use re.fullmatch in email validator to reject trailing newlines (#39234) (#39320)
Co-authored-by: Asuka Minato <i@asukaminato.eu.org>
2026-07-23 04:19:44 +00:00
zyssyz123GitHubautofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2b8e40af32 fix(auth): validate account before accepting invitations (#39438)
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2026-07-23 03:56:32 +00:00
yyhandGitHub 625ed2a0e7 fix(workflow): hide Agent V2 in chatflow (#39439) 2026-07-23 03:37:13 +00:00
林玮 (Jade Lin)GitHubautofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
45711eb6dd chore(api): cloud use presigned download url on api site (#39436)
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2026-07-23 03:34:49 +00:00
Asuka MinatoandGitHub fd703739b5 test: use sqlite3 session in test_async_workflow_service (#38692) 2026-07-23 03:34:10 +00:00
Asuka MinatoandGitHub 82c8741c73 test: use sqlite3 session in test_hitl_service_api (#38685) 2026-07-23 03:33:01 +00:00
Asuka MinatoandGitHub 78023bf50d test: use sqlite3 session in test_conversation (#38684) 2026-07-23 03:32:17 +00:00
Asuka MinatoGitHubautofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
0ad985515b test: move password reset coverage to unit tests (#38936)
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2026-07-23 03:16:06 +00:00
David ParkandGitHub da2177c7b2 fix(api): send valid body in external knowledge validation probe (#39410) 2026-07-23 02:52:52 +00:00
8d293023cc feat: gate cloud analytics behind cookie consent (#39408)
Co-authored-by: CodingOnStar <hanxujiang@dify.com>
2026-07-23 02:40:54 +00:00
yyhGitHubautofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
6736f4005b fix(web): improve import DSL dialog states (#39432)
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2026-07-23 02:26:59 +00:00
Stephen ZhouGitHubautofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
bd8f0104d6 feat(dataset): expose New RAG KnowledgeFS contracts (#39314)
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2026-07-23 01:48:36 +00:00
yyhandGitHub 018fe7a9d3 fix(dify-ui): preserve link semantics in button story (#39430) 2026-07-23 01:07:08 +00:00
非法操作GitHubautofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>WH-2099
d5788cc019 feat: support tool multi-select input (#39346)
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
Co-authored-by: WH-2099 <wh2099@pm.me>
2026-07-23 00:38:54 +00:00
zyssyz123andGitHub 4da4fa72cd fix(agent): refresh stale inline preview drafts (#39415) 2026-07-22 12:54:09 +00:00
平衡世界的BOYGitHubautofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
8853ed99a5 fix: prevent RBAC role names overflowing settings panel (#39412)
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2026-07-22 12:44:29 +00:00
Stephen ZhouGitHubautofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
34a5ca191b feat(dataset): add New Knowledge list and empty state (#39300)
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2026-07-22 12:00:50 +00:00
Asuka MinatoandGitHub 1271cfcf3f test: use sqlite3 session in test_workflow_events_openapi (#38683) 2026-07-22 11:25:14 +00:00
Asuka MinatoandGitHub 2a0b1a8a63 test: use sqlite3 session in test_runtime_credentials (#38682) 2026-07-22 09:50:31 +00:00
Asuka MinatoandGitHub 4a2e92f43f test: use sqlite3 session in test_plugin_wraps (#38681) 2026-07-22 09:49:54 +00:00
Asuka MinatoandGitHub 84889b88ec test: use sqlite3 session in test_init_validate (#38680) 2026-07-22 09:44:29 +00:00
Asuka MinatoandGitHub 6f034d2c93 test: use sqlite3 session in test_tags (#38679) 2026-07-22 09:43:41 +00:00
f91ea49414 test: use sqlite3 session in test_app_import_api (#38674)
Co-authored-by: Byron Wang <byron@dify.ai>
2026-07-22 09:43:30 +00:00
yyhGitHubautofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
62db37c403 fix(web): improve DSL export feedback (#39409)
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2026-07-22 09:40:47 +00:00
Asuka MinatoandGitHub de07730548 test: use sqlite3 session in test_snippet_workflow_draft_variable (#38678) 2026-07-22 09:20:51 +00:00
Asuka MinatoandGitHub 9b2aa8b216 test: use sqlite3 session in test_snippet_workflow (#38677) 2026-07-22 09:20:21 +00:00
Asuka MinatoandGitHub 8ee3a7eabc test: use sqlite3 session in test_rag_pipeline_workflow (#38676) 2026-07-22 09:19:25 +00:00
zyssyz123GitHubautofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
0f9fffb7a2 fix(agent): isolate build and preview chat conversations (#39405)
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2026-07-22 09:17:55 +00:00
Asuka MinatoandGitHub 187501f53e test: use sqlite3 session in test_reset_encrypt_key_pair (#38673) 2026-07-22 09:17:34 +00:00
Wu TianweiandGitHub 03fad2e041 chore: Update permission tip across i18n locales (#39406) 2026-07-22 08:54:37 +00:00
yyhGitHubautofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
acb5ee29e1 test(e2e): validate generated console contracts (#39400)
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2026-07-22 07:48:37 +00:00
林玮 (Jade Lin)andGitHub c5aadfe557 fix(api,billing): invalidate vector space cache after cleanup (#39404) 2026-07-22 07:30:16 +00:00
c76ff4c38c test: use sqlite3 session in test_base_app_runner (#38740)
Co-authored-by: Byron.wang <byron@dify.ai>
2026-07-22 07:21:22 +00:00
yyhandGitHub 4b355b7039 fix(ci): avoid duplicate post-merge e2e runs (#39401) 2026-07-22 06:45:18 +00:00
林玮 (Jade Lin)andGitHub a3654d6a7d fix(oauth): reauth after accepting invitation (#39366) 2026-07-22 05:59:04 +00:00
yyhandGitHub 855464e7b4 chore: clean up CODEOWNERS (#39398) 2026-07-22 05:34:54 +00:00
yyhGitHubautofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
05a25943e7 fix(e2e): align fixtures with generated contracts (#39394)
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2026-07-22 05:09:23 +00:00
Asuka MinatoandGitHub c5d471dbdd test: use sqlite3 session in test_model_config_api (#38675) 2026-07-22 04:53:13 +00:00
Asuka MinatoandGitHub ba449890a9 test: use sqlite3 session in test_app_runner_conversation_variables (#38687) 2026-07-22 04:53:00 +00:00
Asuka MinatoandGitHub 072953a83a test: use sqlite3 session in test_export_service (#38718) 2026-07-22 04:52:19 +00:00
Asuka MinatoandGitHub 7b95e2a75f test: use sqlite3 session in test_generator_api_missing (#38719) 2026-07-22 04:52:06 +00:00
Asuka MinatoGitHubautofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
01efc6eecb test: use SQLite sessions in service API fixtures (#38784)
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2026-07-22 04:51:49 +00:00
Asuka MinatoandGitHub a4c7261bf9 test: use sqlite3 session in test_workflow (#38686) 2026-07-22 04:51:33 +00:00
dependabot[bot]GitHubdependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
0aa04f610e chore: bump pillow from 12.2.0 to 12.3.0 in /dify-agent (#39328)
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2026-07-22 04:23:00 +00:00
Asuka MinatoandGitHub 66afa3bf4a test: use sqlite3 session in test_clear_free_plan_tenant_expired_logs (#38693) 2026-07-22 04:16:21 +00:00
dependabot[bot]GitHubdependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
c0b991c5f9 chore: bump google.golang.org/grpc from 1.82.0 to 1.82.1 in /dify-agent-runtime (#39386)
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2026-07-22 04:06:51 +00:00
dependabot[bot]GitHubdependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
d2aea76dec chore: bump setuptools from 82.0.1 to 83.0.0 in /dify-agent (#39387)
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2026-07-22 04:06:30 +00:00
dependabot[bot]GitHubdependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
bc21972878 chore: bump pyasn1 from 0.6.3 to 0.6.4 in /dify-agent (#39388)
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2026-07-22 04:06:08 +00:00
dependabot[bot]GitHubdependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
389a7608bf chore: bump gitpython from 3.1.50 to 3.1.52 in /api (#39389)
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2026-07-22 04:05:53 +00:00
dependabot[bot]GitHubdependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
3abbab4798 chore: bump pyasn1 from 0.6.3 to 0.6.4 in /api (#39390)
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2026-07-22 04:05:40 +00:00
Wu TianweiandGitHub 84f3c410c4 fix(datasets): update empty state handling and permissions messaging (#39360) 2026-07-22 03:57:35 +00:00
yyhGitHubautofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
04f9026724 fix(web): show unavailable state for disabled Web Apps (#39392)
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2026-07-22 03:32:40 +00:00
Xiyuan ChenandGitHub 3f0f57c594 fix: apply configured timeout to enterprise inner API requests (#39335) 2026-07-22 02:56:08 +00:00
Asuka MinatoandGitHub 79a5b31bc6 test: move console OAuth coverage to unit tests (#38923) 2026-07-22 02:27:55 +00:00
Asuka MinatoandGitHub f35655a5bb test: use sqlite3 session in test_human_input_forms (#38777) 2026-07-22 02:27:30 +00:00
97489d5a44 docs: note minimum Docker Compose version (#39374)
Co-authored-by: zq <zhouquan1511@163.com>
2026-07-22 02:27:30 +00:00
Asuka MinatoandGitHub e9bd8741f4 test: use sqlite3 session in test_auth_wraps (#38760) 2026-07-22 02:23:37 +00:00
Asuka MinatoandGitHub 33acaa558e test: use SQLite sessions in core workflow (#39109) 2026-07-22 02:18:56 +00:00
Asuka MinatoandGitHub b38caf3cdb test: use SQLite sessions in services core (#39111) 2026-07-22 02:15:01 +00:00
Asuka MinatoandGitHub cb2b36f1aa test: use SQLite sessions in services enterprise (#39113) 2026-07-22 02:13:52 +00:00
Asuka MinatoandGitHub 2d15743b96 test: use SQLite sessions in services misc (#39114) 2026-07-22 02:11:52 +00:00
yyhandGitHub d5e5227c6e chore(deps): upgrade Next.js to 16.2.11 (#39384) 2026-07-22 02:04:05 +00:00
yyhGitHubautofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
9b432d0d29 fix: enforce tool provider type contracts (#39380)
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2026-07-22 01:30:55 +00:00
Wu TianweiandGitHub 5216ee1d20 feat: add WebSocket support to dev proxy with cookie rewriting (#39370) 2026-07-22 01:14:27 +00:00
ba8ce362d7 fix(api): PaginatedResult.pages should be 0 for an empty result set (#39229)
Co-authored-by: Loi Nguyen <1948922+lntutor@users.noreply.github.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-22 01:11:14 +00:00
634 changed files with 43098 additions and 8409 deletions
@@ -32,12 +32,11 @@ Keep this skill focused on Cucumber, Playwright, and package-level E2E guidance.
- `e2e/` uses Cucumber for scenarios and Playwright as the browser layer.
- `DifyWorld` is the per-scenario context object. Type `this` as `DifyWorld` and use `async function`, not arrow functions.
- Keep glue organized by capability under `e2e/features/step-definitions/`; use `common/` only for broadly reusable steps.
- Browser session behavior comes from `features/support/hooks.ts`:
- default: authenticated session with shared storage state
- `@unauthenticated`: clean browser context
- `@authenticated`: readability/selective-run tag only unless implementation changes
- `@fresh`: only for `e2e:full*` flows
- Treat `e2e/AGENTS.md`, `features/support/hooks.ts`, and the Cucumber configuration as the owners of current session and tag semantics. Verify them when behavior depends on session state instead of copying a tag inventory into this skill.
- Do not import Playwright Test runner patterns that bypass the current Cucumber + `DifyWorld` architecture unless the task is explicitly about changing that architecture.
- Perform the behavior under test through Playwright. APIs are allowed for setup, seed preparation, persistence polling, and cleanup, but ordinary Console JSON and representable multipart operations must use the scenario- or process-owned generated oRPC client with request and response validation enabled. Keep the setup/cleanup API identity independent from an unauthenticated or logged-out behavior browser.
- Consume generated operations directly. Do not add one-to-one API wrappers, handwritten endpoint URLs, response DTO casts, duplicate schemas, global mutable clients, or TanStack Query caching in Cucumber. Keep helpers only for real fixture construction, multi-operation orchestration, invariants, polling, derived test views, or protocol adapters.
- Keep SSE, binary, redirect-only, external-service, and readiness exceptions centralized under their protocol owner. A contract mismatch must fail and be fixed at the backend schema owner followed by regeneration; never weaken validation to make E2E pass.
## Workflow
@@ -66,7 +65,7 @@ Keep this skill focused on Cucumber, Playwright, and package-level E2E guidance.
- If a product element has real user-facing semantics but no accessible name, prefer fixing that accessible contract over adding a test id.
5. Validate narrowly.
- Run the narrowest tagged scenario or flow that exercises the change.
- Run `vpr lint --fix --quiet` from the repository root and `pnpm -C e2e type-check`.
- Run the package-required static checks documented in `e2e/AGENTS.md`.
- Broaden verification only when the change affects hooks, tags, setup, or shared step semantics.
## Review Checklist
@@ -77,6 +76,8 @@ Keep this skill focused on Cucumber, Playwright, and package-level E2E guidance.
- Are locators user-facing and assertions web-first?
- Does the change introduce hidden coupling across scenarios, tags, or instance state?
- Does it document or implement behavior that differs from the real hooks or configuration?
- Does setup/cleanup use the generated client directly, with any remaining helper owning more than a one-to-one endpoint forward?
- Is every raw HTTP call a documented protocol or infrastructure exception rather than an ordinary Console operation?
Lead findings with correctness, flake risk, and architecture drift.
+17 -44
View File
@@ -8,7 +8,6 @@
# Lint bulk suppression baselines.
/oxlint-suppressions.json
/eslint-suppressions.json
# CODEOWNERS file
/.github/CODEOWNERS @laipz8200 @crazywoola
@@ -33,31 +32,9 @@
# Backend (default owner, more specific rules below will override)
/api/ @QuantumGhost
# Backend - MCP
/api/core/mcp/ @Nov1c444
/api/core/entities/mcp_provider.py @Nov1c444
/api/services/tools/mcp_tools_manage_service.py @Nov1c444
/api/controllers/mcp/ @Nov1c444
/api/controllers/console/app/mcp_server.py @Nov1c444
# Backend - Tests
/api/tests/ @laipz8200 @QuantumGhost
/api/tests/**/*mcp* @Nov1c444
# Backend - Workflow - Engine (Core graph execution engine)
/api/core/workflow/graph_engine/ @laipz8200 @QuantumGhost
/api/core/workflow/runtime/ @laipz8200 @QuantumGhost
/api/core/workflow/graph/ @laipz8200 @QuantumGhost
/api/core/workflow/graph_events/ @laipz8200 @QuantumGhost
/api/core/workflow/node_events/ @laipz8200 @QuantumGhost
# Backend - Workflow - Nodes (Agent, Iteration, Loop, LLM)
/api/core/workflow/nodes/agent/ @Nov1c444
/api/core/workflow/nodes/iteration/ @Nov1c444
/api/core/workflow/nodes/loop/ @Nov1c444
/api/core/workflow/nodes/llm/ @Nov1c444
# Backend - RAG (Retrieval Augmented Generation)
/api/core/rag/ @JohnJyong
/api/services/rag_pipeline/ @JohnJyong
@@ -111,7 +88,6 @@
/api/core/app/layers/trigger_post_layer.py @CourTeous33
/api/services/trigger/ @CourTeous33
/api/models/trigger.py @CourTeous33
/api/fields/workflow_trigger_fields.py @CourTeous33
/api/repositories/workflow_trigger_log_repository.py @CourTeous33
/api/repositories/sqlalchemy_workflow_trigger_log_repository.py @CourTeous33
/api/libs/schedule_utils.py @CourTeous33
@@ -136,11 +112,11 @@
/api/controllers/console/billing/ @hj24 @zyssyz123
# Backend - Enterprise
/api/configs/enterprise/ @GarfieldDai @GareArc
/api/services/enterprise/ @GarfieldDai @GareArc
/api/services/feature_service.py @GarfieldDai @GareArc
/api/controllers/console/feature.py @GarfieldDai @GareArc
/api/controllers/web/feature.py @GarfieldDai @GareArc
/api/configs/enterprise/ @GareArc
/api/services/enterprise/ @GareArc
/api/services/feature_service.py @GareArc
/api/controllers/console/feature.py @GareArc
/api/controllers/web/feature.py @GareArc
# Backend - Database Migrations
/api/migrations/ @snakevash @laipz8200 @MRZHUH
@@ -153,7 +129,6 @@
# Frontend - Platform and Features
/web/config/ @lyzno1
/web/contract/ @lyzno1
/web/env.ts @lyzno1
/web/features/ @lyzno1
/web/hooks/ @lyzno1
@@ -212,7 +187,6 @@
/web/app/components/rag-pipeline/store/ @iamjoel @zxhlyh
# Frontend - RAG - Documents List
/web/app/components/datasets/documents/list.tsx @iamjoel @WTW0313
/web/app/components/datasets/documents/create-from-pipeline/ @iamjoel @WTW0313
# Frontend - RAG - Segments List
@@ -231,22 +205,22 @@
/web/app/components/plugins/marketplace/ @iamjoel @Yessenia-d
# Frontend - Login and Registration
/web/app/signin/ @douxc @iamjoel
/web/app/signup/ @douxc @iamjoel
/web/app/reset-password/ @douxc @iamjoel
/web/app/install/ @douxc @iamjoel
/web/app/init/ @douxc @iamjoel
/web/app/forgot-password/ @douxc @iamjoel
/web/app/account/ @douxc @iamjoel
/web/app/signin/ @iamjoel
/web/app/signup/ @iamjoel
/web/app/reset-password/ @iamjoel
/web/app/install/ @iamjoel
/web/app/init/ @iamjoel
/web/app/forgot-password/ @iamjoel
/web/app/account/ @iamjoel
# Frontend - Service Authentication
/web/service/base.ts @douxc @iamjoel
/web/service/base.ts @iamjoel
# Frontend - WebApp Authentication and Access Control
/web/app/(shareLayout)/components/ @douxc @iamjoel
/web/app/(shareLayout)/webapp-signin/ @douxc @iamjoel
/web/app/(shareLayout)/webapp-reset-password/ @douxc @iamjoel
/web/app/components/app/app-access-control/ @douxc @iamjoel
/web/app/(shareLayout)/components/ @iamjoel
/web/app/(shareLayout)/webapp-signin/ @iamjoel
/web/app/(shareLayout)/webapp-reset-password/ @iamjoel
/web/app/components/app/app-access-control/ @iamjoel
# Frontend - Explore Page
/web/app/components/explore/ @CodingOnStar @iamjoel
@@ -265,7 +239,6 @@
/web/app/components/base/**/*.spec.tsx @hyoban @CodingOnStar
# Frontend - Utils and Hooks
/web/utils/classnames.ts @iamjoel @zxhlyh
/web/utils/time.ts @iamjoel @zxhlyh
/web/utils/format.ts @iamjoel @zxhlyh
/web/utils/clipboard.ts @iamjoel @zxhlyh
+2
View File
@@ -335,6 +335,8 @@ jobs:
- check-changes
if: needs.pre_job.outputs.should_skip != 'true' && needs.check-changes.outputs.e2e-changed == 'true'
uses: ./.github/workflows/web-e2e.yml
with:
run-external-runtime: false
secrets: inherit
web-e2e-skip:
+16
View File
@@ -26,19 +26,30 @@ jobs:
external_e2e:
- 'e2e/features/agent-v2/**'
- 'e2e/features/step-definitions/agent-v2/**'
- 'e2e/features/step-definitions/common/**'
- 'e2e/features/support/**'
- 'e2e/fixtures/auth.ts'
- 'e2e/fixtures/test-materials/**'
- 'e2e/scripts/**'
- 'e2e/support/**'
- 'e2e/cucumber.config.ts'
- 'e2e/package.json'
- 'e2e/test-env.ts'
- 'e2e/tsconfig.json'
- 'e2e/tsx-register.js'
- 'package.json'
- 'pnpm-lock.yaml'
- '.nvmrc'
- '.github/workflows/post-merge.yml'
- '.github/workflows/web-e2e.yml'
- '.github/actions/setup-web/**'
- 'docker/docker-compose.middleware.yaml'
- 'docker/envs/middleware.env.example'
- 'dify-agent/**'
- 'dify-agent-runtime/**'
- 'api/pyproject.toml'
- 'api/uv.lock'
- 'api/tests/integration_tests/.env.example'
- 'api/clients/agent_backend/**'
- 'api/core/app/apps/agent_app/**'
- 'api/core/workflow/nodes/agent_v2/**'
@@ -48,8 +59,13 @@ jobs:
- 'api/services/plugin/**'
- 'api/core/tools/**'
- 'api/services/tools/**'
- 'packages/contracts/package.json'
- 'packages/contracts/generated/api/console/agent/**'
- 'packages/contracts/generated/api/console/apps/**'
- 'packages/contracts/generated/api/console/datasets/**'
- 'packages/contracts/generated/api/console/orpc.gen.ts'
- 'packages/contracts/generated/api/console/workspaces/**'
- 'packages/contracts/generated/api/service/**'
- 'web/features/agent-v2/**'
- 'web/app/(commonLayout)/agents/**'
- 'web/app/(commonLayout)/@detailSidebar/agents/**'
+7 -4
View File
@@ -4,9 +4,9 @@ on:
workflow_call:
inputs:
run-external-runtime:
required: false
description: Run only the prepared and external runtime suite instead of the core suites.
required: true
type: boolean
default: false
permissions:
contents: read
@@ -46,6 +46,7 @@ jobs:
run: uv sync --project api --dev
- name: Run E2E support unit tests
if: ${{ !inputs.run-external-runtime }}
working-directory: ./e2e
run: vp run test:unit
@@ -54,6 +55,7 @@ jobs:
run: vp run e2e:install
- name: Run isolated source-api and built-web Cucumber E2E tests
if: ${{ !inputs.run-external-runtime }}
working-directory: ./e2e
env:
E2E_ADMIN_EMAIL: e2e-admin@example.com
@@ -64,7 +66,7 @@ jobs:
run: vp run e2e:full
- name: Preserve Chromium E2E report and logs
if: ${{ !cancelled() }}
if: ${{ !cancelled() && !inputs.run-external-runtime }}
run: |
if [[ -d e2e/cucumber-report ]]; then
mv e2e/cucumber-report e2e/cucumber-report-non-external
@@ -74,6 +76,7 @@ jobs:
fi
- name: Run WebKit keyboard and browser smoke tests
if: ${{ !inputs.run-external-runtime }}
working-directory: ./e2e
env:
E2E_ADMIN_EMAIL: e2e-admin@example.com
@@ -99,7 +102,7 @@ jobs:
vp run e2e -- --tags '@browser-smoke'
- name: Preserve WebKit E2E report and logs
if: ${{ !cancelled() }}
if: ${{ !cancelled() && !inputs.run-external-runtime }}
run: |
if [[ -d e2e/cucumber-report ]]; then
mv e2e/cucumber-report e2e/cucumber-report-webkit
+1 -1
View File
@@ -71,7 +71,7 @@ Dify is an open-source LLM app development platform. Its intuitive interface com
<br/>
The easiest way to start the Dify server is through [Docker Compose](docker/docker-compose.yaml). Before running Dify with the following commands, make sure that [Docker](https://docs.docker.com/get-docker/) and [Docker Compose](https://docs.docker.com/compose/install/) are installed on your machine:
The easiest way to start the Dify server is through [Docker Compose](docker/docker-compose.yaml). Before running Dify with the following commands, make sure that [Docker](https://docs.docker.com/get-docker/) and Docker Compose v2.24.0 or later are installed on your machine:
```bash
cd dify
+20 -7
View File
@@ -10,6 +10,7 @@ from extensions.ext_database import db
from libs.login import current_account_with_tenant
from models.dataset import Dataset
from models.model import App
from services.agent.roster_service import AgentRosterService
from services.enterprise.rbac_service import RBACService
__all__ = ["RBACPermission", "RBACResourceScope", "enforce_rbac_access", "rbac_permission_required"]
@@ -51,7 +52,7 @@ def enforce_rbac_access(
check_resource_type = None if resource_type == RBACResourceScope.WORKSPACE else resource_type
resource_id = None
if resource_required and check_resource_type:
resource_id = _extract_resource_id(resource_type, path_args)
resource_id = _extract_resource_id(resource_type, tenant_id, path_args)
if _is_resource_owned_by_current_user(tenant_id, account_id, resource_type, resource_id):
return
allowed = RBACService.CheckAccess.check(
@@ -131,11 +132,14 @@ def _is_resource_owned_by_current_user(
return False
def _extract_resource_id(resource_type: RBACResourceScope, path_args: dict[str, object] | None = None) -> str:
def _extract_resource_id(
resource_type: RBACResourceScope, tenant_id: str, path_args: dict[str, object] | None = None
) -> str:
"""Extract the resource ID from matched path arguments.
Some legacy route classes use neutral names such as ``resource_id`` for
app/dataset resources, and Agent App routes use ``agent_id`` as the app id.
app/dataset resources, and Agent routes carry ``agent_id``, which is
resolved to the App backing that Agent.
Dataset endpoints behind a rag-pipeline route contain ``pipeline_id``
instead of ``dataset_id``. In that case we look up the associated
``Dataset`` row via ``Dataset.pipeline_id``.
@@ -146,10 +150,19 @@ def _extract_resource_id(resource_type: RBACResourceScope, path_args: dict[str,
matched_args = {**view_args, **(path_args or {})}
if resource_type == RBACResourceScope.APP:
app_id = matched_args.get("app_id") or matched_args.get("agent_id") or matched_args.get("resource_id")
if not app_id:
raise ValueError("Missing app_id in request path")
return str(app_id)
app_id = matched_args.get("app_id")
if app_id:
return str(app_id)
agent_id = matched_args.get("agent_id")
if agent_id:
authz_app_id = AgentRosterService(db.session).peek_authz_app_id(tenant_id=tenant_id, agent_id=str(agent_id))
return authz_app_id or str(agent_id)
resource_id = matched_args.get("resource_id")
if resource_id:
return str(resource_id)
raise ValueError("Missing app_id in request path")
if resource_type == RBACResourceScope.DATASET:
dataset_id = matched_args.get("dataset_id") or matched_args.get("resource_id")
@@ -230,6 +230,7 @@ class WorkflowAgentComposerSaveToRosterApi(Resource):
@account_initialization_required
@edit_permission_required
@rbac_permission_required(RBACResourceScope.APP, RBACPermission.APP_EDIT)
@rbac_permission_required(RBACResourceScope.WORKSPACE, RBACPermission.AGENT_MANAGE, resource_required=False)
@with_current_user_id
@with_current_tenant_id
@with_session
@@ -439,6 +440,7 @@ class SnippetAgentComposerSaveToRosterApi(Resource):
@rbac_permission_required(
RBACResourceScope.WORKSPACE, RBACPermission.SNIPPETS_CREATE_AND_MODIFY, resource_required=False
)
@rbac_permission_required(RBACResourceScope.WORKSPACE, RBACPermission.AGENT_MANAGE, resource_required=False)
@with_current_user_id
@with_current_tenant_id
@with_session
@@ -478,6 +480,7 @@ class AgentComposerApi(Resource):
@account_initialization_required
@edit_permission_required
@rbac_permission_required(RBACResourceScope.APP, RBACPermission.APP_EDIT)
@rbac_permission_required(RBACResourceScope.WORKSPACE, RBACPermission.AGENT_MANAGE, resource_required=False)
@with_current_user_id
@with_current_tenant_id
@with_session
+60 -3
View File
@@ -62,7 +62,7 @@ from libs.datetime_utils import parse_time_range
from libs.helper import dump_response
from libs.login import login_required
from models import Account
from models.agent import Agent, AgentStatus
from models.agent import Agent, AgentConfigDraftType, AgentStatus
from models.agent_config_entities import AgentSoulConfig
from models.enums import ApiTokenType
from models.model import ApiToken, App, IconType
@@ -266,6 +266,13 @@ class AgentDebugConversationRefreshResponse(BaseModel):
debug_conversation_message_count: int = 0
class AgentDebugConversationRefreshPayload(BaseModel):
draft_type: AgentConfigDraftType = Field(
default=AgentConfigDraftType.DEBUG_BUILD,
description="Agent draft surface whose conversation should be refreshed",
)
class AgentPublishPayload(BaseModel):
version_note: str | None = Field(default=None, description="Optional note for this published Agent version")
@@ -309,6 +316,7 @@ register_schema_models(
AgentAppCopyPayload,
AgentPublishPayload,
AgentBuildDraftCheckoutPayload,
AgentDebugConversationRefreshPayload,
ComposerSavePayload,
AgentApiStatusPayload,
AgentInviteOptionsQuery,
@@ -392,6 +400,7 @@ def _serialize_agent_app_detail(
tenant_id=app_model.tenant_id,
agent_id=agent.id,
account_id=current_user.id,
draft_type=AgentConfigDraftType.DEBUG_BUILD,
commit=False,
)
message_count = roster_service.count_agent_app_debug_conversation_messages(
@@ -439,6 +448,7 @@ def _serialize_agent_app_pagination(session: Session, app_pagination, *, tenant_
tenant_id=tenant_id,
agents=list(agents_by_app_id.values()),
account_id=current_user.id,
draft_type=AgentConfigDraftType.DEBUG_BUILD,
)
payload = AgentAppPagination.model_validate(
app_pagination,
@@ -529,9 +539,23 @@ def _parse_observability_time_range(start: str | None, end: str | None, account:
def _query_values(name: str, alias_name: str | None = None) -> list[str]:
values = request.args.getlist(name)
def _get_values(field_name: str) -> list[str]:
values = request.args.getlist(field_name)
indexed_values: list[tuple[int, list[str]]] = []
prefix = f"{field_name}["
for key in request.args:
if not key.startswith(prefix) or not key.endswith("]"):
continue
index = key[len(prefix) : -1]
if index.isdigit():
indexed_values.append((int(index), request.args.getlist(key)))
for _, items in sorted(indexed_values):
values.extend(items)
return values
values = _get_values(name)
if alias_name:
values.extend(request.args.getlist(alias_name))
values.extend(_get_values(alias_name))
return [value.strip() for value in values if value.strip()]
@@ -542,6 +566,7 @@ class AgentAppListApi(Resource):
@setup_required
@login_required
@account_initialization_required
@rbac_permission_required(RBACResourceScope.WORKSPACE, RBACPermission.AGENT_MANAGE, resource_required=False)
@with_current_user
@with_current_tenant_id
@with_session
@@ -579,6 +604,7 @@ class AgentAppListApi(Resource):
@login_required
@account_initialization_required
@edit_permission_required
@rbac_permission_required(RBACResourceScope.WORKSPACE, RBACPermission.AGENT_MANAGE, resource_required=False)
@with_current_user
@with_current_tenant_id
@with_session
@@ -620,6 +646,7 @@ class AgentAppApi(Resource):
@login_required
@account_initialization_required
@edit_permission_required
@rbac_permission_required(RBACResourceScope.WORKSPACE, RBACPermission.AGENT_MANAGE, resource_required=False)
@with_current_user
@with_current_tenant_id
@with_session
@@ -645,6 +672,7 @@ class AgentAppApi(Resource):
@login_required
@account_initialization_required
@edit_permission_required
@rbac_permission_required(RBACResourceScope.WORKSPACE, RBACPermission.AGENT_MANAGE, resource_required=False)
@with_current_tenant_id
@with_session
def delete(self, session: Session, tenant_id: str, agent_id: UUID):
@@ -655,6 +683,16 @@ class AgentAppApi(Resource):
@console_ns.route("/agent/<uuid:agent_id>/debug-conversation/refresh")
class AgentDebugConversationRefreshApi(Resource):
@console_ns.expect(console_ns.models[AgentDebugConversationRefreshPayload.__name__])
@console_ns.doc(
params={
"payload": {
"in": "body",
"required": False,
"schema": {"$ref": f"#/components/schemas/{AgentDebugConversationRefreshPayload.__name__}"},
}
}
)
@console_ns.response(
200,
"Agent debug conversation refreshed",
@@ -669,10 +707,12 @@ class AgentDebugConversationRefreshApi(Resource):
@with_current_tenant_id
@with_session
def post(self, session: Session, tenant_id: str, current_user: Account, agent_id: UUID):
args = AgentDebugConversationRefreshPayload.model_validate(request.get_json(silent=True) or {})
debug_conversation_id = _agent_roster_service(session).refresh_agent_app_debug_conversation_id(
tenant_id=tenant_id,
agent_id=str(agent_id),
account_id=current_user.id,
draft_type=args.draft_type,
)
return AgentDebugConversationRefreshResponse(
debug_conversation_id=debug_conversation_id,
@@ -690,6 +730,7 @@ class AgentPublishApi(Resource):
@login_required
@account_initialization_required
@edit_permission_required
@rbac_permission_required(RBACResourceScope.WORKSPACE, RBACPermission.AGENT_MANAGE, resource_required=False)
@with_current_user
@with_current_tenant_id
@with_session
@@ -712,6 +753,7 @@ class AgentBuildDraftCheckoutApi(Resource):
@login_required
@account_initialization_required
@edit_permission_required
@rbac_permission_required(RBACResourceScope.WORKSPACE, RBACPermission.AGENT_MANAGE, resource_required=False)
@with_current_user
@with_current_tenant_id
@with_session
@@ -729,6 +771,7 @@ class AgentBuildDraftCheckoutApi(Resource):
@console_ns.route("/agent/<uuid:agent_id>/build-draft")
class AgentBuildDraftApi(Resource):
@console_ns.response(200, "Agent build draft", console_ns.models[AgentBuildDraftResponse.__name__])
@console_ns.response(404, "Agent build draft not found")
@setup_required
@login_required
@account_initialization_required
@@ -787,6 +830,7 @@ class AgentBuildDraftApplyApi(Resource):
@login_required
@account_initialization_required
@edit_permission_required
@rbac_permission_required(RBACResourceScope.WORKSPACE, RBACPermission.AGENT_MANAGE, resource_required=False)
@with_current_user
@with_current_tenant_id
@with_session
@@ -809,6 +853,7 @@ class AgentAppCopyApi(Resource):
@login_required
@account_initialization_required
@edit_permission_required
@rbac_permission_required(RBACResourceScope.WORKSPACE, RBACPermission.AGENT_MANAGE, resource_required=False)
@with_current_user
@with_current_tenant_id
@with_session
@@ -834,6 +879,7 @@ class AgentApiAccessApi(Resource):
@setup_required
@login_required
@account_initialization_required
@rbac_permission_required(RBACResourceScope.WORKSPACE, RBACPermission.AGENT_MANAGE, resource_required=False)
@with_current_tenant_id
@with_session(write=False)
def get(self, session: Session, tenant_id: str, agent_id: UUID):
@@ -850,6 +896,7 @@ class AgentApiStatusApi(Resource):
@login_required
@is_admin_or_owner_required
@account_initialization_required
@rbac_permission_required(RBACResourceScope.WORKSPACE, RBACPermission.AGENT_MANAGE, resource_required=False)
@rbac_permission_required(RBACResourceScope.APP, RBACPermission.APP_RELEASE_AND_VERSION)
@with_current_tenant_id
@with_session
@@ -868,6 +915,7 @@ class AgentApiKeyListApi(BaseApiKeyListResource):
token_prefix = "app-"
@console_ns.response(200, "Agent service API keys", console_ns.models[ApiKeyList.__name__])
@rbac_permission_required(RBACResourceScope.WORKSPACE, RBACPermission.AGENT_MANAGE, resource_required=False)
@with_current_tenant_id
@with_session(write=False)
def get(self, session: Session, tenant_id: str, agent_id: UUID) -> dict[str, object]:
@@ -878,6 +926,7 @@ class AgentApiKeyListApi(BaseApiKeyListResource):
@console_ns.response(400, "Maximum keys exceeded")
@with_current_tenant_id
@edit_permission_required
@rbac_permission_required(RBACResourceScope.WORKSPACE, RBACPermission.AGENT_MANAGE, resource_required=False)
@rbac_permission_required(RBACResourceScope.APP, RBACPermission.APP_RELEASE_AND_VERSION)
@with_session
def post(self, session: Session, tenant_id: str, agent_id: UUID) -> tuple[dict[str, object], int]:
@@ -897,6 +946,7 @@ class AgentApiKeyApi(BaseApiKeyResource):
@console_ns.response(204, "Agent service API key deleted")
@with_current_user
@with_current_tenant_id
@rbac_permission_required(RBACResourceScope.WORKSPACE, RBACPermission.AGENT_MANAGE, resource_required=False)
@rbac_permission_required(RBACResourceScope.APP, RBACPermission.APP_RELEASE_AND_VERSION)
@with_session
def delete(
@@ -942,6 +992,7 @@ class AgentLogsApi(Resource):
@setup_required
@login_required
@account_initialization_required
@rbac_permission_required(RBACResourceScope.WORKSPACE, RBACPermission.AGENT_MANAGE, resource_required=False)
@with_current_user
@with_current_tenant_id
@with_session(write=False)
@@ -980,6 +1031,7 @@ class AgentLogMessagesApi(Resource):
@setup_required
@login_required
@account_initialization_required
@rbac_permission_required(RBACResourceScope.WORKSPACE, RBACPermission.AGENT_MANAGE, resource_required=False)
@with_current_user
@with_current_tenant_id
@with_session(write=False)
@@ -1018,6 +1070,7 @@ class AgentLogSourcesApi(Resource):
@setup_required
@login_required
@account_initialization_required
@rbac_permission_required(RBACResourceScope.WORKSPACE, RBACPermission.AGENT_MANAGE, resource_required=False)
@with_current_user
@with_current_tenant_id
@with_session(write=False)
@@ -1038,6 +1091,7 @@ class AgentStatisticsSummaryApi(Resource):
@setup_required
@login_required
@account_initialization_required
@rbac_permission_required(RBACResourceScope.WORKSPACE, RBACPermission.AGENT_MANAGE, resource_required=False)
@with_current_user
@with_current_tenant_id
@with_session(write=False)
@@ -1063,6 +1117,7 @@ class AgentRosterVersionsApi(Resource):
@setup_required
@login_required
@account_initialization_required
@rbac_permission_required(RBACResourceScope.WORKSPACE, RBACPermission.AGENT_MANAGE, resource_required=False)
@with_current_tenant_id
@with_session(write=False)
def get(self, session: Session, tenant_id: str, agent_id: UUID):
@@ -1078,6 +1133,7 @@ class AgentRosterVersionDetailApi(Resource):
@setup_required
@login_required
@account_initialization_required
@rbac_permission_required(RBACResourceScope.WORKSPACE, RBACPermission.AGENT_MANAGE, resource_required=False)
@with_current_tenant_id
@with_session(write=False)
def get(self, session: Session, tenant_id: str, agent_id: UUID, version_id: UUID):
@@ -1098,6 +1154,7 @@ class AgentRosterVersionRestoreApi(Resource):
@login_required
@account_initialization_required
@edit_permission_required
@rbac_permission_required(RBACResourceScope.WORKSPACE, RBACPermission.AGENT_MANAGE, resource_required=False)
@with_current_user
@with_current_tenant_id
@with_session
+4
View File
@@ -12,6 +12,7 @@ from werkzeug.exceptions import Forbidden
from configs import dify_config
from controllers.common.schema import register_response_schema_models
from controllers.common.session import with_session
from controllers.console.app.wraps import agent_manage_required_for_agent_app
from fields.base import ResponseModel
from libs.helper import dump_response, to_timestamp
from libs.login import login_required
@@ -194,6 +195,7 @@ class AppApiKeyListResource(BaseApiKeyListResource):
@console_ns.doc(params={"resource_id": "App ID"})
@console_ns.response(200, "API keys retrieved successfully", console_ns.models[ApiKeyList.__name__])
@with_current_tenant_id
@agent_manage_required_for_agent_app
@with_session(write=False)
def get(self, session: Session, current_tenant_id: str, resource_id: UUID) -> dict[str, object]:
"""Get all API keys for an app"""
@@ -210,6 +212,7 @@ class AppApiKeyListResource(BaseApiKeyListResource):
@with_current_tenant_id
@edit_permission_required
@rbac_permission_required(RBACResourceScope.APP, RBACPermission.APP_RELEASE_AND_VERSION)
@agent_manage_required_for_agent_app
@with_session
def post(self, session: Session, current_tenant_id: str, resource_id: UUID) -> tuple[dict[str, object], int]:
"""Create a new API key for an app"""
@@ -233,6 +236,7 @@ class AppApiKeyResource(BaseApiKeyResource):
@with_current_user
@with_current_tenant_id
@rbac_permission_required(RBACResourceScope.APP, RBACPermission.APP_RELEASE_AND_VERSION)
@agent_manage_required_for_agent_app
@with_session
def delete(
self,
+34 -17
View File
@@ -9,7 +9,7 @@ from flask_restx import Resource
from pydantic import AliasChoices, BaseModel, Field, ValidationInfo, computed_field, field_validator, model_validator
from sqlalchemy import select
from sqlalchemy.orm import Session
from werkzeug.exceptions import BadRequest, NotFound
from werkzeug.exceptions import BadRequest, Forbidden, NotFound
from configs import dify_config
from controllers.common.app_access import resolve_app_access_filter
@@ -23,7 +23,7 @@ from controllers.common.schema import (
register_schema_models,
)
from controllers.console import console_ns
from controllers.console.app.wraps import get_app_model, with_session
from controllers.console.app.wraps import agent_manage_required_for_agent_app, get_app_model, with_session
from controllers.console.workspace.models import LoadBalancingPayload
from controllers.console.wraps import (
RBACPermission,
@@ -75,6 +75,7 @@ from services.entities.knowledge_entities.knowledge_entities import (
WeightModel,
WeightVectorSetting,
)
from services.errors.account import NoPermissionError
from services.feature_service import FeatureService
from tasks.initialize_created_app_rbac_access_task import initialize_created_app_rbac_access_task
@@ -246,7 +247,7 @@ class ModelConfigPartial(ResponseModel):
return to_timestamp(value)
class ModelConfig(ResponseModel):
class AppModelConfigResponse(ResponseModel):
opening_statement: str | None = None
suggested_questions: Any | None = Field(
default=None, validation_alias=AliasChoices("suggested_questions_list", "suggested_questions")
@@ -419,7 +420,7 @@ class AppDetail(AppResponseModel):
icon_background: str | None = None
enable_site: bool
enable_api: bool
model_config_: ModelConfig | None = Field(
model_config_: AppModelConfigResponse | None = Field(
default=None,
validation_alias=AliasChoices("app_model_config", "model_config"),
alias="model_config",
@@ -525,7 +526,13 @@ def _enrich_app_list_items(session: Session, *, apps: Sequence[App], tenant_id:
register_enum_models(console_ns, RetrievalMethod, WorkflowExecutionStatus, DatasetPermissionEnum)
register_response_schema_models(
console_ns, RedirectUrlResponse, SimpleResultResponse, AppImportResponse, AppTraceResponse
console_ns,
RedirectUrlResponse,
SimpleResultResponse,
AppImportResponse,
AppTraceResponse,
AppModelConfigResponse,
AppDetail,
)
register_schema_models(
@@ -544,10 +551,8 @@ register_schema_models(
Tag,
WorkflowPartial,
ModelConfigPartial,
ModelConfig,
AppDetailSiteResponse,
DeletedTool,
AppDetail,
AppExportResponse,
Segmentation,
PreProcessingRule,
@@ -823,6 +828,7 @@ class AppApi(Resource):
@account_initialization_required
@edit_permission_required
@rbac_permission_required(RBACResourceScope.APP, RBACPermission.APP_EDIT)
@agent_manage_required_for_agent_app
@with_session
@get_app_model(mode=None)
def put(self, session: Session, app_model: App):
@@ -857,6 +863,7 @@ class AppApi(Resource):
@account_initialization_required
@edit_permission_required
@rbac_permission_required(RBACResourceScope.APP, RBACPermission.APP_DELETE)
@agent_manage_required_for_agent_app
@with_session
@get_app_model
def delete(self, session: Session, app_model: App):
@@ -881,6 +888,7 @@ class AppCopyApi(Resource):
@account_initialization_required
@edit_permission_required
@rbac_permission_required(RBACResourceScope.APP, RBACPermission.APP_CREATE_AND_MANAGEMENT)
@agent_manage_required_for_agent_app
@with_current_user
@with_current_tenant_id
@get_app_model(mode=None)
@@ -892,16 +900,19 @@ class AppCopyApi(Resource):
with Session(db.engine, expire_on_commit=False) as session:
import_service = AppDslService(session)
yaml_content = import_service.export_dsl(app_model=app_model, session=session, include_secret=True)
result = import_service.import_app(
account=current_user,
import_mode=ImportMode.YAML_CONTENT,
yaml_content=yaml_content,
name=args.name,
description=args.description,
icon_type=args.icon_type,
icon=args.icon,
icon_background=args.icon_background,
)
try:
result = import_service.import_app(
account=current_user,
import_mode=ImportMode.YAML_CONTENT,
yaml_content=yaml_content,
name=args.name,
description=args.description,
icon_type=args.icon_type,
icon=args.icon,
icon_background=args.icon_background,
)
except NoPermissionError as e:
raise Forbidden(str(e))
if result.status == ImportStatus.FAILED:
session.rollback()
return dump_response(AppImportResponse, result), 400
@@ -955,6 +966,7 @@ class AppExportApi(Resource):
@account_initialization_required
@edit_permission_required
@rbac_permission_required(RBACResourceScope.APP, RBACPermission.APP_IMPORT_EXPORT_DSL)
@agent_manage_required_for_agent_app
@get_app_model
def get(self, app_model: App):
"""Export app"""
@@ -979,6 +991,7 @@ class AppPublishToCreatorsPlatformApi(Resource):
@account_initialization_required
@edit_permission_required
@rbac_permission_required(RBACResourceScope.APP, RBACPermission.APP_IMPORT_EXPORT_DSL)
@agent_manage_required_for_agent_app
@with_current_user_id
@get_app_model(mode=None)
def post(self, current_user_id: str, app_model: App):
@@ -1009,6 +1022,7 @@ class AppNameApi(Resource):
@account_initialization_required
@edit_permission_required
@rbac_permission_required(RBACResourceScope.APP, RBACPermission.APP_EDIT)
@agent_manage_required_for_agent_app
@with_session
@get_app_model(mode=None)
def post(self, session: Session, app_model: App):
@@ -1036,6 +1050,7 @@ class AppIconApi(Resource):
@account_initialization_required
@edit_permission_required
@rbac_permission_required(RBACResourceScope.APP, RBACPermission.APP_EDIT)
@agent_manage_required_for_agent_app
@with_session
@get_app_model(mode=None)
def post(self, session: Session, app_model: App):
@@ -1069,6 +1084,7 @@ class AppSiteStatus(Resource):
@account_initialization_required
@edit_permission_required
@rbac_permission_required(RBACResourceScope.APP, RBACPermission.APP_RELEASE_AND_VERSION)
@agent_manage_required_for_agent_app
@with_session
@get_app_model(mode=None)
def post(self, session: Session, app_model: App):
@@ -1096,6 +1112,7 @@ class AppApiStatus(Resource):
@is_admin_or_owner_required
@account_initialization_required
@rbac_permission_required(RBACResourceScope.APP, RBACPermission.APP_RELEASE_AND_VERSION)
@agent_manage_required_for_agent_app
@with_session
@get_app_model(mode=None)
def post(self, session: Session, app_model: App):
+21 -13
View File
@@ -1,6 +1,7 @@
from flask_restx import Resource
from pydantic import BaseModel, Field
from sqlalchemy.orm import Session
from werkzeug.exceptions import Forbidden
from configs import dify_config
from controllers.common.schema import register_enum_models, register_schema_models
@@ -28,6 +29,7 @@ from services.app_dsl_service import (
)
from services.enterprise.enterprise_service import EnterpriseService
from services.entities.dsl_entities import CheckDependenciesResult, ImportStatus
from services.errors.account import NoPermissionError
from services.feature_service import FeatureService
from .. import console_ns
@@ -91,18 +93,21 @@ class AppImportApi(Resource):
import_service = AppDslService(session)
# Import app
account = current_user
result = import_service.import_app(
account=account,
import_mode=args.mode,
yaml_content=args.yaml_content,
yaml_url=args.yaml_url,
name=args.name,
description=args.description,
icon_type=args.icon_type,
icon=args.icon,
icon_background=args.icon_background,
app_id=args.app_id,
)
try:
result = import_service.import_app(
account=account,
import_mode=args.mode,
yaml_content=args.yaml_content,
yaml_url=args.yaml_url,
name=args.name,
description=args.description,
icon_type=args.icon_type,
icon=args.icon,
icon_background=args.icon_background,
app_id=args.app_id,
)
except NoPermissionError as e:
raise Forbidden(str(e))
if result.status == ImportStatus.FAILED:
session.rollback()
else:
@@ -157,7 +162,10 @@ class AppImportConfirmApi(Resource):
import_service = AppDslService(session)
# Confirm import
account = current_user
result = import_service.confirm_import(import_id=import_id, account=account)
try:
result = import_service.confirm_import(import_id=import_id, account=account)
except NoPermissionError as e:
raise Forbidden(str(e))
if result.status == ImportStatus.FAILED:
session.rollback()
else:
+37 -13
View File
@@ -49,6 +49,7 @@ from libs import helper
from libs.helper import uuid_value
from libs.login import login_required
from models import Account
from models.agent import AgentConfigDraftType
from models.model import App, AppMode
from services.agent.errors import AgentNotFoundError
from services.agent.roster_service import AgentRosterService
@@ -343,23 +344,40 @@ class AgentChatMessageStopApi(Resource):
def _resolve_current_user_agent_debug_conversation_id(
*, session: Session, current_tenant_id: str, current_user: Account, app_model: App, agent_id: str | None
*,
session: Session,
current_tenant_id: str,
current_user: Account,
app_model: App,
agent_id: str | None,
draft_type: AgentConfigDraftType,
start_new: bool = False,
) -> str:
roster_service = AgentRosterService(session)
if agent_id:
return roster_service.get_or_create_agent_app_debug_conversation_id(
tenant_id=current_tenant_id,
agent_id=agent_id,
account_id=current_user.id,
)
"""Resolve or rotate the current editor's conversation within one draft surface.
agent = roster_service.get_app_backing_agent(tenant_id=current_tenant_id, app_id=str(app_model.id))
if agent is None:
raise AgentNotFoundError()
return roster_service.get_or_create_agent_app_debug_conversation_id(
``start_new`` rotates the scoped mapping through ``AgentRosterService`` so
the old runtime session is retired before the new conversation is used.
Continuations and Build chat keep resolving the existing mapping.
"""
roster_service = AgentRosterService(session)
resolved_agent_id = agent_id
if not resolved_agent_id:
agent = roster_service.get_app_backing_agent(tenant_id=current_tenant_id, app_id=str(app_model.id))
if agent is None:
raise AgentNotFoundError()
resolved_agent_id = agent.id
resolve_conversation = (
roster_service.refresh_agent_app_debug_conversation_id
if start_new
else roster_service.get_or_create_agent_app_debug_conversation_id
)
return resolve_conversation(
tenant_id=current_tenant_id,
agent_id=agent.id,
agent_id=resolved_agent_id,
account_id=current_user.id,
draft_type=draft_type,
)
@@ -376,12 +394,17 @@ def _create_chat_message(
args = args_model.model_dump(exclude_none=True, by_alias=True)
if AppMode.value_of(app_model.mode) == AppMode.AGENT:
draft_type = AgentConfigDraftType(args_model.draft_type)
# Preview follows the normal chat contract: an omitted/empty conversation ID starts a new
# conversation. Build chat keeps its stable mapping so build drafts and finalization stay continuous.
debug_conversation_id = _resolve_current_user_agent_debug_conversation_id(
session=session,
current_tenant_id=current_tenant_id or app_model.tenant_id,
current_user=current_user,
app_model=app_model,
agent_id=agent_id,
draft_type=draft_type,
start_new=draft_type == AgentConfigDraftType.DRAFT and not args_model.conversation_id,
)
if args_model.conversation_id and args_model.conversation_id != debug_conversation_id:
raise NotFound("Conversation Not Exists.")
@@ -418,6 +441,7 @@ def _create_build_chat_finalization_message(
current_user=current_user,
app_model=app_model,
agent_id=agent_id,
draft_type=AgentConfigDraftType.DEBUG_BUILD,
)
args: dict[str, Any] = {
"query": _BUILD_CHAT_FINALIZATION_QUERY,
+3 -1
View File
@@ -10,7 +10,7 @@ from constants.languages import supported_language
from controllers.common.schema import register_schema_models
from controllers.common.session import with_session
from controllers.console import console_ns
from controllers.console.app.wraps import get_app_model
from controllers.console.app.wraps import agent_manage_required_for_agent_app, get_app_model
from controllers.console.wraps import (
RBACPermission,
RBACResourceScope,
@@ -93,6 +93,7 @@ class AppSite(Resource):
@login_required
@edit_permission_required
@rbac_permission_required(RBACResourceScope.APP, RBACPermission.APP_RELEASE_AND_VERSION)
@agent_manage_required_for_agent_app
@account_initialization_required
@with_current_user
@with_session
@@ -145,6 +146,7 @@ class AppSiteAccessTokenReset(Resource):
@login_required
@is_admin_or_owner_required
@rbac_permission_required(RBACResourceScope.APP, RBACPermission.APP_RELEASE_AND_VERSION)
@agent_manage_required_for_agent_app
@account_initialization_required
@with_current_user
@with_session
+16 -13
View File
@@ -359,6 +359,12 @@ class WorkflowPublishResponse(ResponseModel):
created_at: int
class SyncDraftWorkflowResponse(ResponseModel):
result: str
hash: str
updated_at: int
class WorkflowRestoreResponse(ResponseModel):
result: str
hash: str
@@ -441,6 +447,7 @@ register_response_schema_models(
WorkflowOnlineUsersByApp,
WorkflowOnlineUsersResponse,
WorkflowPublishResponse,
SyncDraftWorkflowResponse,
WorkflowRestoreResponse,
DefaultBlockConfigsResponse,
DefaultBlockConfigResponse,
@@ -556,14 +563,7 @@ class DraftWorkflowApi(Resource):
@console_ns.response(
200,
"Draft workflow synced successfully",
console_ns.model(
"SyncDraftWorkflowResponse",
{
"result": fields.String,
"hash": fields.String,
"updated_at": fields.String,
},
),
console_ns.models[SyncDraftWorkflowResponse.__name__],
)
@console_ns.response(400, "Invalid workflow configuration")
@console_ns.response(403, "Permission denied")
@@ -618,11 +618,14 @@ class DraftWorkflowApi(Resource):
except VariableError as e:
raise InvalidArgumentError(description=str(e))
return {
"result": "success",
"hash": workflow.unique_hash,
"updated_at": TimestampField().format(workflow.updated_at or workflow.created_at),
}
return dump_response(
SyncDraftWorkflowResponse,
{
"result": "success",
"hash": workflow.unique_hash,
"updated_at": TimestampField().format(workflow.updated_at or workflow.created_at),
},
)
@console_ns.route("/apps/<uuid:app_id>/advanced-chat/workflows/draft/run")
+48 -1
View File
@@ -12,14 +12,22 @@ from typing import cast, overload
from sqlalchemy import select
from sqlalchemy.orm import Session
from configs import dify_config
from controllers.common.session import with_session
from controllers.common.wraps import RBACPermission, RBACResourceScope, enforce_rbac_access
from controllers.console.app.error import AppNotFoundError
from extensions.ext_database import db
from libs.login import current_account_with_tenant
from models import App, AppMode, TrialApp
from models.agent import AgentScope
from services.recommended_app_service import RecommendedAppService
__all__ = ["get_app_model", "get_app_model_with_trial", "with_session"]
__all__ = [
"agent_manage_required_for_agent_app",
"get_app_model",
"get_app_model_with_trial",
"with_session",
]
def _load_app_model(session: Session, app_id: str) -> App | None:
@@ -48,6 +56,45 @@ def _load_app_model_with_trial(session: Session, app_id: str) -> App | None:
return app_model
def agent_manage_required_for_agent_app[**P, R](view: Callable[P, R]) -> Callable[P, R]:
"""Gate generic app management routes that target an Agent App.
A hidden workflow-only backing App only reuses the App runtime and is not
part of the general app management plane, so generic routes reject it
outright. Managing a roster Agent App mutates the roster Agent behind it
(rename/icon sync, archive, API enablement), so it additionally requires
workspace ``agent.manage`` on top of the route's existing App permission
checks when RBAC is enabled. A no-op for non-agent Apps. Must be placed
above ``get_app_model`` so the ``app_id`` path parameter is still present.
"""
@wraps(view)
def decorated(*args: P.args, **kwargs: P.kwargs) -> R:
raw_app_id = kwargs.get("app_id") or kwargs.get("resource_id")
if raw_app_id is not None:
app_model = _load_app_model_from_scoped_session(str(raw_app_id))
binding = (
app_model.agent_app_binding_with_session(session=db.session(), include_archived=True)
if app_model is not None
else None
)
if binding is not None:
if binding.scope == AgentScope.WORKFLOW_ONLY:
raise AppNotFoundError()
if dify_config.RBAC_ENABLED:
current_user, current_tenant_id = current_account_with_tenant()
enforce_rbac_access(
tenant_id=current_tenant_id,
account_id=current_user.id,
resource_type=RBACResourceScope.WORKSPACE,
scene=RBACPermission.AGENT_MANAGE,
resource_required=False,
)
return view(*args, **kwargs)
return decorated
def _get_injected_session(args: tuple[object, ...]) -> Session | None:
"""Return the request session inserted by `with_session`, if this handler has been migrated."""
if len(args) < 2:
+14
View File
@@ -7,10 +7,13 @@ from configs import dify_config
from constants.languages import supported_language
from controllers.common.schema import query_params_from_model, register_schema_models
from controllers.console import console_ns
from controllers.console.auth.error import InvitationAccountMismatchError
from controllers.console.error import AccountInFreezeError, AlreadyActivateError
from extensions.ext_database import db
from libs.datetime_utils import naive_utc_now
from libs.helper import EmailStr, timezone
from libs.login import current_account_with_tenant
from libs.token import extract_access_token
from models import AccountStatus
from models.account import TenantAccountJoin, TenantAccountRole
from services.account_service import RegisterService, TenantService
@@ -136,6 +139,12 @@ class ActivateApi(Resource):
)
@console_ns.response(400, "Already activated or invalid token")
def post(self):
"""Accept an invitation without letting an existing session act for another account.
Token-only activation remains available for legacy clients. When the request already
carries a console session, that session must belong to the account encoded in the
invitation before the token is consumed or tenant membership is changed.
"""
args = ActivatePayload.model_validate(console_ns.payload)
normalized_request_email = args.email.lower() if args.email else None
@@ -146,6 +155,11 @@ class ActivateApi(Resource):
raise AlreadyActivateError()
account = invitation["account"]
if extract_access_token(request):
current_account, _ = current_account_with_tenant()
if current_account.id != account.id:
raise InvitationAccountMismatchError()
if dify_config.BILLING_ENABLED and BillingService.is_email_in_freeze(account.email):
raise AccountInFreezeError()
+6
View File
@@ -13,6 +13,12 @@ class InvalidEmailError(BaseHTTPException):
code = 400
class InvitationAccountMismatchError(BaseHTTPException):
error_code = "invitation_account_mismatch"
description = "This invitation was sent to another account. Please sign in with the invited account."
code = 403
class PasswordMismatchError(BaseHTTPException):
error_code = "password_mismatch"
description = "The passwords do not match."
+35 -21
View File
@@ -6,6 +6,7 @@ from flask import current_app, redirect, request
from flask_restx import Resource
from pydantic import BaseModel, Field
from werkzeug.exceptions import Unauthorized
from werkzeug.wrappers import Response
from configs import dify_config
from constants.languages import languages
@@ -127,6 +128,20 @@ def _preferred_interface_language(language: str | None = None) -> str:
return languages[0]
def _redirect_with_console_session(account: Account, target_url: str) -> Response:
"""Create a console session and attach its cookies to a redirect response."""
token_pair = AccountService.login(
account=account,
session=db.session(),
ip_address=extract_remote_ip(request),
)
response = redirect(target_url)
set_access_token_to_cookie(request, response, token_pair.access_token)
set_refresh_token_to_cookie(request, response, token_pair.refresh_token)
set_csrf_token_to_cookie(request, response, token_pair.csrf_token)
return response
@console_ns.route("/oauth/login/<provider>")
class OAuthLogin(Resource):
@console_ns.doc("oauth_login")
@@ -195,16 +210,26 @@ class OAuthCallback(Resource):
return redirect(f"{dify_config.CONSOLE_WEB_URL}/signin?message={urllib.parse.quote(str(e))}")
if invite_token and RegisterService.is_valid_invite_token(invite_token):
invitation = RegisterService.get_invitation_by_token(token=invite_token)
if invitation:
invitation_email = invitation.get("email", None)
invitation_email_normalized = (
invitation_email.lower() if isinstance(invitation_email, str) else invitation_email
)
if invitation_email_normalized != user_info.email.lower():
return redirect(f"{dify_config.CONSOLE_WEB_URL}/signin?message=Invalid invitation token.")
invitation = RegisterService.get_invitation_if_token_valid(
None,
None,
invite_token,
session=db.session(),
)
if not invitation:
return redirect(f"{dify_config.CONSOLE_WEB_URL}/signin?message=Invalid invitation token.")
if invitation["data"]["email"].lower() != user_info.email.lower():
message = "This invitation was sent to another account. Please sign in with the invited account."
query = urllib.parse.urlencode({"message": message, "invite_token": invite_token})
return redirect(f"{dify_config.CONSOLE_WEB_URL}/signin?{query}")
return redirect(f"{dify_config.CONSOLE_WEB_URL}/signin/invite-settings?invite_token={invite_token}")
account = invitation["account"]
if account.status == AccountStatus.BANNED:
return redirect(f"{dify_config.CONSOLE_WEB_URL}/signin?message=Account is banned.")
AccountService.link_account_integrate(provider, user_info.id, account, session=db.session())
target_url = f"{dify_config.CONSOLE_WEB_URL}/signin/invite-settings?invite_token={invite_token}"
return _redirect_with_console_session(account, target_url)
try:
account, oauth_new_user = _generate_account(provider, user_info, timezone=timezone, language=language)
@@ -239,21 +264,10 @@ class OAuthCallback(Resource):
"?message=Workspace not found, please contact system admin to invite you to join in a workspace."
)
token_pair = AccountService.login(
account=account,
session=db.session(),
ip_address=extract_remote_ip(request),
)
target_url = _get_redirect_target(redirect_url)
query_char = "&" if "?" in target_url else "?"
target_url = f"{target_url}{query_char}oauth_new_user={str(oauth_new_user).lower()}"
response = redirect(target_url)
set_access_token_to_cookie(request, response, token_pair.access_token)
set_refresh_token_to_cookie(request, response, token_pair.refresh_token)
set_csrf_token_to_cookie(request, response, token_pair.csrf_token)
return response
return _redirect_with_console_session(account, target_url)
def _get_account_by_openid_or_email(provider: str, user_info: OAuthUserInfo) -> Account | None:
@@ -56,6 +56,7 @@ class OAuthProviderTokenResponse(BaseModel):
class OAuthProviderAccountResponse(BaseModel):
id: str
name: str
email: str
avatar: str | None = None
@@ -251,6 +252,7 @@ class OAuthServerUserAccountApi(Resource):
def post(self, oauth_provider_app: OAuthProviderApp, account: Account):
return jsonable_encoder(
{
"id": account.id,
"name": account.name,
"email": account.email,
"avatar": account.avatar,
+132 -45
View File
@@ -8,8 +8,9 @@ can be validated explicitly against the pinned KnowledgeFS contract during devel
Console auth and contract-specific dataset RBAC run before forwarding. Request
bodies are capped at 64 MiB, JSON and binary responses have separate bounds,
SSE responses remain streaming with a bounded idle read timeout, and only safe
response headers are exposed. Upstream 401 responses become 502 so they cannot
trigger Dify browser-session recovery; resource-level 403 responses remain 403.
response headers are exposed. Operation-specific upstream error mappings are
applied before Console JSON error handling; the default maps 401 to 502 so it
cannot trigger browser-session recovery and preserves resource-level 403.
"""
from __future__ import annotations
@@ -27,9 +28,11 @@ from werkzeug.exceptions import (
BadGateway,
Forbidden,
GatewayTimeout,
HTTPException,
NotFound,
RequestEntityTooLarge,
ServiceUnavailable,
default_exceptions,
)
from configs import dify_config
@@ -41,21 +44,28 @@ from controllers.console.wraps import (
)
from core.helper import ssrf_proxy
from libs.login import current_account_with_tenant, login_required
from services.knowledge_fs_operations import KnowledgeFSMethod
from services.knowledge_fs_proxy import (
KnowledgeFSAccessDeniedError,
KnowledgeFSAuthorization,
KnowledgeFSConfigurationError,
KnowledgeFSMethod,
KnowledgeFSRouteNotAllowedError,
KnowledgeFSTimeoutError,
KnowledgeFSTransportError,
KnowledgeFSUpstreamResponse,
authorize_knowledge_fs_request,
get_knowledge_fs_operation,
proxy_authorized_knowledge_fs_request,
proxy_knowledge_fs_request,
)
logger = logging.getLogger(__name__)
type _KnowledgeFSRequestForwarder = Callable[
[str | None, str | None, bytes | None, bytes | None],
KnowledgeFSUpstreamResponse,
]
_MAX_PROXY_BODY_BYTES = 64 * 1024 * 1024
_RESPONSE_HEADER_ALLOWLIST = (
"Cache-Control",
@@ -128,27 +138,25 @@ def _translate_proxy_error(exc: Exception, *, tenant_id: str) -> NoReturn:
def _knowledge_fs_operation_access_required(
view: Callable[[KnowledgeFSMethod, str], ResponseReturnValue],
view: Callable[[KnowledgeFSAuthorization], ResponseReturnValue],
) -> Callable[[KnowledgeFSMethod, str], ResponseReturnValue]:
"""Authorize one declared operation before billing and request-body work."""
@wraps(view)
def decorated(method: KnowledgeFSMethod, upstream_path: str) -> ResponseReturnValue:
try:
operation = get_knowledge_fs_operation(method, upstream_path)
except KnowledgeFSRouteNotAllowedError as exc:
raise NotFound() from exc
current_user, tenant_id = current_account_with_tenant()
try:
authorize_knowledge_fs_request(
authorization = authorize_knowledge_fs_request(
account=current_user,
tenant_id=tenant_id,
operation=operation,
method=method,
path=upstream_path,
)
except KnowledgeFSRouteNotAllowedError as exc:
raise NotFound() from exc
except KnowledgeFSAccessDeniedError as exc:
_translate_proxy_error(exc, tenant_id=tenant_id)
return view(method, upstream_path)
return view(authorization)
return decorated
@@ -190,21 +198,26 @@ def _proxy_response(
"""Expose raw content, status, and allowlisted headers from KnowledgeFS.
Raises:
BadGateway: KnowledgeFS rejects the configured server credential.
Forbidden: KnowledgeFS denies the account access to the requested resource.
HTTPException: KnowledgeFS returns a status normalized by the operation contract.
"""
upstream = upstream_result.response
if upstream.status_code == HTTPStatus.UNAUTHORIZED:
mapped_status = dict(upstream_result.operation.error_status_map).get(upstream.status_code)
if mapped_status is not None:
upstream.close()
logger.error(
"KnowledgeFS rejected the Dify server credential with HTTP %s for tenant_id=%s",
upstream.status_code,
tenant_id,
)
raise BadGateway("KnowledgeFS authentication failed")
if upstream.status_code == HTTPStatus.FORBIDDEN:
upstream.close()
raise Forbidden()
description = "KnowledgeFS upstream request failed"
if upstream.status_code == HTTPStatus.UNAUTHORIZED:
description = "KnowledgeFS authentication failed"
logger.error(
"KnowledgeFS rejected the Dify server credential with HTTP %s for tenant_id=%s",
upstream.status_code,
tenant_id,
)
exception_type = default_exceptions.get(mapped_status)
if exception_type is None:
exception = HTTPException(description)
exception.code = mapped_status
raise exception
raise exception_type(description)
allowed_header_names = dict.fromkeys(
name.lower() for name in (*_RESPONSE_HEADER_ALLOWLIST, *contract_response_headers)
@@ -237,26 +250,21 @@ def _proxy_response(
return Response(content, status=upstream.status_code, headers=headers)
def _proxy_request(method: KnowledgeFSMethod, upstream_path: str) -> Response:
"""Forward the current raw request and return its filtered upstream response.
The call performs one outbound KnowledgeFS request. Integration failures are
converted to Console HTTP exceptions for the outer JSON error adapter.
"""
def _proxy_current_request(
*,
method: KnowledgeFSMethod,
tenant_id: str,
forward: _KnowledgeFSRequestForwarder,
) -> Response:
"""Forward the current raw request through one preconfigured service entry."""
if not dify_config.KNOWLEDGE_FS_ENABLED:
raise NotFound()
current_user, tenant_id = current_account_with_tenant()
try:
proxy_result = proxy_knowledge_fs_request(
account=current_user,
method=method,
path=upstream_path,
tenant_id=tenant_id,
accept=request.headers.get("Accept"),
content_type=request.content_type,
query=request.query_string or None,
body=_request_body() if method != "GET" else None,
request_headers=request.headers,
proxy_result = forward(
request.headers.get("Accept"),
request.content_type,
request.query_string or None,
_request_body() if method != "GET" else None,
)
except (
KnowledgeFSConfigurationError,
@@ -274,20 +282,99 @@ def _proxy_request(method: KnowledgeFSMethod, upstream_path: str) -> Response:
)
def _proxy_request(
method: KnowledgeFSMethod,
upstream_path: str,
) -> Response:
"""Authorize and forward the current request through the combined service use case."""
if not dify_config.KNOWLEDGE_FS_ENABLED:
raise NotFound()
current_user, tenant_id = current_account_with_tenant()
def forward(
accept: str | None,
content_type: str | None,
query: bytes | None,
body: bytes | None,
) -> KnowledgeFSUpstreamResponse:
return proxy_knowledge_fs_request(
account=current_user,
method=method,
path=upstream_path,
tenant_id=tenant_id,
accept=accept,
content_type=content_type,
query=query,
body=body,
request_headers=request.headers,
)
return _proxy_current_request(method=method, tenant_id=tenant_id, forward=forward)
def _proxy_authorized_request(authorization: KnowledgeFSAuthorization) -> Response:
"""Forward the current request using one previously authorized operation capability.
Args:
authorization: Request-scoped capability produced before billing and body parsing.
Returns:
The filtered response returned by KnowledgeFS.
Raises:
HTTPException: The integration is disabled or forwarding fails.
"""
operation = authorization.operation
tenant_id = authorization.tenant_id
def forward(
accept: str | None,
content_type: str | None,
query: bytes | None,
body: bytes | None,
) -> KnowledgeFSUpstreamResponse:
return proxy_authorized_knowledge_fs_request(
authorization=authorization,
accept=accept,
content_type=content_type,
query=query,
body=body,
request_headers=request.headers,
)
return _proxy_current_request(method=operation.method, tenant_id=tenant_id, forward=forward)
@_knowledge_fs_enabled
@_knowledge_fs_operation_access_required
@cloud_edition_billing_rate_limit_check("knowledge")
def _proxy_knowledge_fs_non_get(
method: KnowledgeFSMethod,
upstream_path: str,
authorization: KnowledgeFSAuthorization,
) -> ResponseReturnValue:
"""Apply knowledge billing checks to one allowlisted non-GET operation."""
return _proxy_request(method, upstream_path)
return _proxy_authorized_request(authorization)
@bp.route(
"/knowledge-fs/<path:upstream_path>",
methods=["GET", "OPTIONS"],
methods=["OPTIONS"],
provide_automatic_options=False,
)
@_console_api_errors
@_knowledge_fs_enabled
def proxy_knowledge_fs_options(upstream_path: str) -> ResponseReturnValue:
"""Complete a CORS preflight only for an enabled Console operation."""
requested_method = cast(KnowledgeFSMethod, request.headers.get("Access-Control-Request-Method", "").upper())
try:
get_knowledge_fs_operation(requested_method, upstream_path)
except KnowledgeFSRouteNotAllowedError as exc:
raise NotFound() from exc
return Response(status=HTTPStatus.NO_CONTENT)
@bp.route(
"/knowledge-fs/<path:upstream_path>",
methods=["GET"],
provide_automatic_options=False,
)
@_console_api_errors
@@ -67,6 +67,15 @@ from services.plugin.plugin_parameter_service import PluginParameterService
from services.plugin.plugin_permission_service import PluginPermissionService
from services.tools.tools_transform_service import ToolTransformService
_PLUGIN_PACKAGE_UPLOAD_PARAMS = {
"pkg": {
"description": "Plugin package to upload",
"in": "formData",
"type": "file",
"required": True,
}
}
class AutoUpgradeSettingsResponse(TypedDict):
strategy_setting: TenantPluginAutoUpgradeStrategySetting
@@ -645,6 +654,7 @@ class PluginAssetApi(Resource):
@console_ns.route("/workspaces/current/plugin/upload/pkg")
class PluginUploadFromPkgApi(Resource):
@console_ns.doc(consumes=["multipart/form-data"], params=_PLUGIN_PACKAGE_UPLOAD_PARAMS)
@console_ns.response(200, "Success", console_ns.models[PluginDecodeResponse.__name__])
@setup_required
@login_required
+17 -7
View File
@@ -1,6 +1,6 @@
from typing import Any, Self
from pydantic import AliasChoices, Field, computed_field
from pydantic import AliasChoices, Field
from sqlalchemy import select
from werkzeug.exceptions import Forbidden
@@ -9,11 +9,13 @@ from controllers.common.schema import register_response_schema_models
from controllers.web import web_ns
from controllers.web.wraps import WebApiResource
from extensions.ext_database import db
from extensions.storage.storage_type import StorageType
from fields.base import ResponseModel
from libs.helper import build_icon_url
from models.account import Tenant, TenantStatus
from models.model import App, EndUser, Site
from models.model import App, EndUser, IconType, Site
from services.feature_service import FeatureModel, FeatureService
from services.file_service import FileService
class WebSiteResponse(ResponseModel):
@@ -32,11 +34,7 @@ class WebSiteResponse(ResponseModel):
prompt_public: bool | None = None
show_workflow_steps: bool | None = None
use_icon_as_answer_icon: bool | None = None
@computed_field(return_type=str | None) # type: ignore[prop-decorator]
@property
def icon_url(self) -> str | None:
return build_icon_url(self.icon_type, self.icon)
icon_url: str | None = None
class WebModelConfigResponse(ResponseModel):
@@ -88,6 +86,7 @@ class WebAppSiteResponse(ResponseModel):
end_user_id: str | None,
features: FeatureModel,
can_replace_logo: bool,
icon_url: str | None = None,
) -> Self:
custom_config = None
if can_replace_logo:
@@ -102,6 +101,7 @@ class WebAppSiteResponse(ResponseModel):
)
site_response = WebSiteResponse.model_validate(site, from_attributes=True)
site_response.icon_url = icon_url if icon_url is not None else build_icon_url(site.icon_type, site.icon)
if features.billing.enabled and not features.webapp_copyright_enabled:
site_response.copyright = None
site_response.input_placeholder = None
@@ -123,6 +123,15 @@ register_response_schema_models(
)
def _build_site_icon_url(*, site: Site, tenant_id: str) -> str | None:
"""Use direct S3 URLs only in Cloud Mode and preserve preview URLs elsewhere."""
if site.icon_type != IconType.IMAGE or not site.icon:
return None
if dify_config.EDITION == "CLOUD" and StorageType(dify_config.STORAGE_TYPE) == StorageType.S3:
return FileService(db.engine).get_file_presigned_url(file_id=site.icon, tenant_id=tenant_id)
return build_icon_url(site.icon_type, site.icon)
@web_ns.route("/site")
class AppSiteApi(WebApiResource):
@web_ns.doc("Get App Site Info")
@@ -159,4 +168,5 @@ class AppSiteApi(WebApiResource):
end_user_id=end_user.id,
features=features,
can_replace_logo=features.can_replace_logo,
icon_url=_build_site_icon_url(site=site, tenant_id=tenant.id),
).model_dump(mode="json")
+6
View File
@@ -11,6 +11,7 @@ from werkzeug.exceptions import BadRequest, NotFound, Unauthorized
from constants import HEADER_NAME_APP_CODE
from controllers.web.error import WebAppAuthAccessDeniedError, WebAppAuthRequiredError
from core.logging.context import set_identity_context
from extensions.ext_database import db
from libs.passport import PassportService
from libs.token import extract_webapp_passport
@@ -28,6 +29,11 @@ def validate_jwt_token[**P, R](
@wraps(view)
def decorated(*args: P.args, **kwargs: P.kwargs) -> R:
app_model, end_user = decode_jwt_token()
set_identity_context(
tenant_id=end_user.tenant_id,
user_id=end_user.id,
user_type=end_user.type or "end_user",
)
return view(app_model, end_user, *args, **kwargs)
return decorated
+36 -1
View File
@@ -10,12 +10,13 @@ from sqlalchemy.orm import Session
from core.agent.entities import AgentEntity, AgentToolEntity
from core.app.app_config.features.file_upload.manager import FileUploadConfigManager
from core.app.apps.agent_chat.app_config_manager import AgentChatAppConfig
from core.app.apps.base_app_queue_manager import AppQueueManager
from core.app.apps.base_app_queue_manager import AppQueueManager, PublishFrom
from core.app.apps.base_app_runner import AppRunner
from core.app.entities.app_invoke_entities import (
AgentChatAppGenerateEntity,
ModelConfigWithCredentialsEntity,
)
from core.app.entities.queue_entities import QueueUIPartEvent
from core.app.file_access import DatabaseFileAccessController
from core.callback_handler.agent_tool_callback_handler import DifyAgentCallbackHandler
from core.callback_handler.index_tool_callback_handler import DatasetIndexToolCallbackHandler
@@ -23,6 +24,12 @@ from core.memory.token_buffer_memory import TokenBufferMemory
from core.model_manager import ModelInstance
from core.prompt.utils.extract_thread_messages import extract_thread_messages
from core.tools.__base.tool import Tool
from core.tools.entities.ui_entities import (
MessageUIPart,
ToolUIMessage,
build_ui_part_id,
validate_tool_ui_message_batch,
)
from core.tools.tool_manager import ToolManager
from core.tools.utils.dataset_retriever_tool import DatasetRetrieverTool
from extensions.ext_database import db
@@ -352,6 +359,34 @@ class BaseAgentRunner(AppRunner):
db.session.commit()
db.session.close()
def publish_ui_messages(self, *, namespace: str, ui_messages: list[ToolUIMessage]) -> None:
"""Publish validated tool UI messages without adding them to agent observations."""
try:
validate_tool_ui_message_batch(ui_messages)
except ValueError:
logger.warning(
"Ignored tool UI batch that exceeds queue publication limits",
extra={"message_id": self.message.id, "namespace": namespace},
exc_info=True,
)
return
sequences: dict[str, int] = {}
for ui_message in ui_messages:
part_id = build_ui_part_id(namespace, ui_message.surface_id)
sequence = sequences.get(part_id, 0) + 1
sequences[part_id] = sequence
self.queue_manager.publish(
QueueUIPartEvent(
part=MessageUIPart.from_tool_ui_message(
part_id=part_id,
sequence=sequence,
ui_message=ui_message,
)
),
PublishFrom.APPLICATION_MANAGER,
)
def organize_agent_history(self, prompt_messages: list[PromptMessage], *, session: Session) -> list[PromptMessage]:
"""
Organize agent history
+11 -1
View File
@@ -235,6 +235,7 @@ class CotAgentRunner(BaseAgentRunner, ABC):
# action is tool call, invoke tool
tool_invoke_response, tool_invoke_meta = self._handle_invoke_action(
session=session,
agent_thought_id=agent_thought_id,
action=scratchpad.action,
tool_instances=tool_instances,
message_file_ids=message_file_ids,
@@ -306,9 +307,11 @@ class CotAgentRunner(BaseAgentRunner, ABC):
tool_instances: Mapping[str, Tool],
message_file_ids: list[str],
trace_manager: TraceQueueManager | None = None,
agent_thought_id: str | None = None,
) -> tuple[str, ToolInvokeMeta]:
"""
handle invoke action
:param agent_thought_id: namespace for UI parts emitted by this action
:param action: action
:param tool_instances: tool instances
:param message_file_ids: message file ids
@@ -331,7 +334,7 @@ class CotAgentRunner(BaseAgentRunner, ABC):
pass
# invoke tool
tool_invoke_response, message_files, tool_invoke_meta = ToolEngine.agent_invoke(
invoke_result = ToolEngine.agent_invoke(
session=session,
tool=tool_instance,
tool_parameters=tool_call_args,
@@ -342,6 +345,13 @@ class CotAgentRunner(BaseAgentRunner, ABC):
agent_tool_callback=self.agent_callback,
trace_manager=trace_manager,
)
tool_invoke_response = invoke_result.observation
message_files = invoke_result.message_files
tool_invoke_meta = invoke_result.meta
self.publish_ui_messages(
namespace=agent_thought_id or self.message.id,
ui_messages=invoke_result.ui_messages,
)
session.commit()
session.close()
+8 -1
View File
@@ -251,7 +251,7 @@ class FunctionCallAgentRunner(BaseAgentRunner):
}
else:
# invoke tool
tool_invoke_response, message_files, tool_invoke_meta = ToolEngine.agent_invoke(
invoke_result = ToolEngine.agent_invoke(
session=session,
tool=tool_instance,
tool_parameters=tool_call_args,
@@ -265,6 +265,13 @@ class FunctionCallAgentRunner(BaseAgentRunner):
message_id=self.message.id,
conversation_id=self.conversation.id,
)
tool_invoke_response = invoke_result.observation
message_files = invoke_result.message_files
tool_invoke_meta = invoke_result.meta
self.publish_ui_messages(
namespace=tool_call_id,
ui_messages=invoke_result.ui_messages,
)
session.commit()
session.close()
# publish files
+14 -29
View File
@@ -682,42 +682,27 @@ class AgentAppGenerator(MessageBasedAppGenerator):
if draft_type == AgentConfigDraftType.DEBUG_BUILD.value
else AgentConfigDraftType.DRAFT
)
if effective_draft_type == AgentConfigDraftType.DRAFT:
from services.agent.composer_service import AgentComposerService
return AgentComposerService.get_or_create_normal_agent_draft(
session=session,
tenant_id=tenant_id,
agent=agent,
created_by=agent.updated_by or agent.created_by,
)
if not account_id:
raise AgentAppGeneratorError("Build draft requires an account user")
stmt = select(AgentConfigDraft).where(
AgentConfigDraft.tenant_id == tenant_id,
AgentConfigDraft.agent_id == agent.id,
AgentConfigDraft.draft_type == effective_draft_type,
AgentConfigDraft.draft_type == AgentConfigDraftType.DEBUG_BUILD,
AgentConfigDraft.account_id == account_id,
)
if effective_draft_type == AgentConfigDraftType.DEBUG_BUILD:
if not account_id:
raise AgentAppGeneratorError("Build draft requires an account user")
stmt = stmt.where(AgentConfigDraft.account_id == account_id)
else:
stmt = stmt.where(AgentConfigDraft.account_id.is_(None))
draft = session.scalar(stmt.order_by(AgentConfigDraft.updated_at.desc()).limit(1))
if draft is not None:
return draft
if effective_draft_type == AgentConfigDraftType.DEBUG_BUILD:
raise AgentAppGeneratorError("Agent build draft not found")
_, snapshot, agent_soul = AgentAppGenerator._resolve_agent_by_id(
tenant_id=tenant_id,
agent_id=agent.id,
snapshot_id=agent.active_config_snapshot_id,
session=session,
)
draft = AgentConfigDraft(
tenant_id=tenant_id,
agent_id=agent.id,
draft_type=AgentConfigDraftType.DRAFT,
account_id=None,
draft_owner_key="",
base_snapshot_id=snapshot.id,
config_snapshot=agent_soul,
created_by=agent.created_by,
updated_by=agent.updated_by,
)
session.add(draft)
session.flush()
return draft
raise AgentAppGeneratorError("Agent build draft not found")
@staticmethod
def _resolve_agent_by_id(
+58 -2
View File
@@ -52,8 +52,16 @@ from core.app.entities.queue_entities import (
QueueAgentThoughtEvent,
QueueLLMChunkEvent,
QueueMessageEndEvent,
QueueUIPartEvent,
)
from core.repositories.human_input_repository import HumanInputFormRepository, HumanInputFormRepositoryImpl
from core.tools.entities.ui_entities import (
MessageUIPart,
ToolUIMessage,
build_ui_part_id,
parse_tool_ui_messages,
validate_tool_ui_message_batch,
)
from core.workflow.nodes.agent_v2.ask_human_hitl import AskHumanFormBuildError, create_ask_human_form
from core.workflow.nodes.agent_v2.ask_human_resume import build_deferred_tool_results, resolve_ask_human_form
from extensions.ext_database import db
@@ -435,9 +443,29 @@ class _AgentProcessRecorder:
content = part.get("content")
if content is None:
content = part
self._record_tool_observation(tool_call_id=tool_call_id, tool_name=tool_name, observation=content)
thought_id = self._record_tool_observation(
tool_call_id=tool_call_id,
tool_name=tool_name,
observation=content,
)
def _record_tool_observation(self, *, tool_call_id: str | None, tool_name: str | None, observation: Any) -> None:
metadata = part.get("metadata")
if not isinstance(metadata, Mapping) or "dify_ui_messages" not in metadata:
return
try:
ui_messages = parse_tool_ui_messages(metadata["dify_ui_messages"])
except (TypeError, ValueError):
logger.warning("Ignored invalid dify_ui_messages metadata from Agent backend", exc_info=True)
return
self._publish_ui_messages(namespace=tool_call_id or thought_id, ui_messages=ui_messages)
def _record_tool_observation(
self,
*,
tool_call_id: str | None,
tool_name: str | None,
observation: Any,
) -> str:
self._close_thinking_segments()
thought_id = self._lookup_observation_thought(tool_call_id=tool_call_id, tool_name=tool_name)
if thought_id is None:
@@ -445,6 +473,34 @@ class _AgentProcessRecorder:
else:
self._mark_tool_observed(thought_id)
self._update_thought(thought_id, observation=_json_or_text(observation))
return thought_id
def _publish_ui_messages(self, *, namespace: str, ui_messages: list[ToolUIMessage]) -> None:
try:
validate_tool_ui_message_batch(ui_messages)
except ValueError:
logger.warning(
"Ignored Agent backend UI batch that exceeds queue publication limits",
extra={"message_id": self._message_id, "namespace": namespace},
exc_info=True,
)
return
sequences: dict[str, int] = {}
for ui_message in ui_messages:
part_id = build_ui_part_id(namespace, ui_message.surface_id)
sequence = sequences.get(part_id, 0) + 1
sequences[part_id] = sequence
self._queue_manager.publish(
QueueUIPartEvent(
part=MessageUIPart.from_tool_ui_message(
part_id=part_id,
sequence=sequence,
ui_message=ui_message,
)
),
PublishFrom.APPLICATION_MANAGER,
)
def _lookup_tool_thought(self, *, index: int, tool_call_id: str | None) -> str | None:
if tool_call_id and tool_call_id in self._tool_by_call_id:
+9
View File
@@ -7,6 +7,7 @@ from pydantic import BaseModel, ConfigDict, Field
from core.app.entities.agent_strategy import AgentStrategyInfo
from core.rag.entities import RetrievalSourceMetadata
from core.tools.entities.ui_entities import MessageUIPart
from core.workflow.nodes.human_input.pause_reason import PauseReason
from graphon.entities import WorkflowStartReason
from graphon.enums import NodeType, WorkflowNodeExecutionMetadataKey
@@ -43,6 +44,7 @@ class QueueEvent(StrEnum):
REASONING_CHUNK = "reasoning_chunk"
ANNOTATION_REPLY = "annotation_reply"
AGENT_THOUGHT = "agent_thought"
UI_PART = "ui_part"
MESSAGE_FILE = "message_file"
AGENT_LOG = "agent_log"
ERROR = "error"
@@ -457,6 +459,13 @@ class QueueAgentThoughtEvent(AppQueueEvent):
agent_thought_id: str
class QueueUIPartEvent(AppQueueEvent):
"""A validated tool UI surface revision."""
event: QueueEvent = QueueEvent.UI_PART
part: MessageUIPart
class QueueMessageFileEvent(AppQueueEvent):
"""
QueueAgentThoughtEvent entity
+19 -1
View File
@@ -2,10 +2,11 @@ from collections.abc import Mapping, Sequence
from enum import StrEnum
from typing import Any, Literal
from pydantic import BaseModel, ConfigDict, Field, JsonValue
from pydantic import BaseModel, ConfigDict, Field, JsonValue, field_validator
from core.app.entities.agent_strategy import AgentStrategyInfo
from core.rag.entities import RetrievalSourceMetadata
from core.tools.entities.ui_entities import MessageUIPart, validate_ui_part_batch
from core.workflow.nodes.human_input.entities import FormInputConfig, UserActionConfig
from core.workflow.nodes.human_input.pause_reason import DifyHITLEventType
from graphon.entities import WorkflowStartReason
@@ -30,6 +31,14 @@ class TaskStateMetadata(BaseModel):
reasoning: dict[str, str] = Field(default_factory=dict)
"""reasoning_content per LLM node id (separated mode), accumulated across iteration/loop
passes for that node; persisted to message_metadata"""
ui_parts: list[MessageUIPart] = Field(default_factory=list)
"""Latest validated revision of each tool UI part; persisted to message metadata."""
@field_validator("ui_parts")
@classmethod
def _validate_ui_parts(cls, value: list[MessageUIPart]) -> list[MessageUIPart]:
validate_ui_part_batch(value)
return value
class TaskState(BaseModel):
@@ -73,6 +82,7 @@ class StreamEvent(StrEnum):
MESSAGE_FILE = "message_file"
MESSAGE_REPLACE = "message_replace"
AGENT_THOUGHT = "agent_thought"
UI_PART = "ui_part"
AGENT_MESSAGE = "agent_message"
WORKFLOW_STARTED = "workflow_started"
WORKFLOW_PAUSED = "workflow_paused"
@@ -192,6 +202,14 @@ class AgentThoughtStreamResponse(StreamResponse):
message_files: list[str] | None = None
class UIPartStreamResponse(StreamResponse):
"""A tool-owned UI surface revision."""
event: StreamEvent = StreamEvent.UI_PART
id: str
part: MessageUIPart
class AgentMessageStreamResponse(StreamResponse):
"""
AgentMessageStreamResponse entity
@@ -26,6 +26,7 @@ from core.app.entities.queue_entities import (
QueuePingEvent,
QueueRetrieverResourcesEvent,
QueueStopEvent,
QueueUIPartEvent,
)
from core.app.entities.task_entities import (
AgentMessageStreamResponse,
@@ -41,6 +42,7 @@ from core.app.entities.task_entities import (
MessageEndStreamResponse,
StreamEvent,
StreamResponse,
UIPartStreamResponse,
)
from core.app.task_pipeline.based_generate_task_pipeline import BasedGenerateTaskPipeline
from core.app.task_pipeline.message_cycle_manager import MessageCycleManager
@@ -52,6 +54,7 @@ from core.ops.entities.trace_entity import TraceTaskName
from core.ops.ops_trace_manager import TraceQueueManager, TraceTask
from core.prompt.utils.prompt_message_util import PromptMessageUtil
from core.prompt.utils.prompt_template_parser import PromptTemplateParser
from core.tools.entities.ui_entities import upsert_ui_part
from events.message_event import message_was_created
from graphon.file import FileTransferMethod
from graphon.model_runtime.entities.llm_entities import LLMResult, LLMResultChunk, LLMResultChunkDelta, LLMUsage
@@ -311,6 +314,10 @@ class EasyUIBasedGenerateTaskPipeline(BasedGenerateTaskPipeline[EasyUIAppGenerat
agent_thought_response = self._agent_thought_to_stream_response(event)
if agent_thought_response is not None:
yield agent_thought_response
case QueueUIPartEvent():
ui_part_response = self._ui_part_to_stream_response(event)
if ui_part_response is not None:
yield ui_part_response
case QueueMessageFileEvent():
response = self._message_cycle_manager.message_file_to_stream_response(event)
if response:
@@ -526,6 +533,27 @@ class EasyUIBasedGenerateTaskPipeline(BasedGenerateTaskPipeline[EasyUIAppGenerat
task_id=self._application_generate_entity.task_id, id=message_id, answer=answer
)
def _ui_part_to_stream_response(self, event: QueueUIPartEvent) -> UIPartStreamResponse | None:
"""Upsert a UI part revision into persistent metadata and stream it."""
try:
updated_parts = upsert_ui_part(self._task_state.metadata.ui_parts, event.part)
except ValueError:
logger.warning(
"Ignored UI part that exceeds assistant message limits",
extra={"message_id": self._message_id, "part_id": event.part.part_id},
exc_info=True,
)
return None
if updated_parts is None:
return None
self._task_state.metadata.ui_parts = updated_parts
return UIPartStreamResponse(
task_id=self._application_generate_entity.task_id,
id=self._message_id,
part=event.part,
)
def _agent_thought_to_stream_response(self, event: QueueAgentThoughtEvent) -> AgentThoughtStreamResponse | None:
"""
Agent thought to stream response.
+46 -44
View File
@@ -21,6 +21,7 @@ from core.model_manager import ModelInstance, ModelManager
from core.rag.cleaner.clean_processor import CleanProcessor
from core.rag.datasource.keyword.keyword_factory import Keyword
from core.rag.docstore.dataset_docstore import DatasetDocumentStore
from core.rag.embedding.token_counter import calculate_segment_token_counts
from core.rag.extractor.entity.datasource_type import DatasourceType
from core.rag.extractor.entity.extract_setting import ExtractSetting, NotionInfo, WebsiteInfo
from core.rag.index_processor.constant.index_type import IndexStructureType, IndexTechniqueType
@@ -113,17 +114,25 @@ class IndexingRunner:
current_user=current_user,
session=session,
)
token_counts = calculate_segment_token_counts(dataset=dataset, documents=documents)
total_tokens = sum(token_counts)
# save segment
self._load_segments(dataset, requeried_document, documents, session)
self._load_segments(
session=session,
dataset=dataset,
dataset_document=requeried_document,
documents=documents,
token_counts=token_counts,
)
session.commit()
# load
self._load(
index_processor=index_processor,
session=session,
dataset=dataset,
dataset_document=requeried_document,
documents=documents,
session=session,
total_tokens=total_tokens,
)
except DocumentIsPausedError:
raise DocumentIsPausedError(f"Document paused, document id: {document_id}")
@@ -190,17 +199,25 @@ class IndexingRunner:
current_user=current_user,
session=session,
)
token_counts = calculate_segment_token_counts(dataset=dataset, documents=documents)
total_tokens = sum(token_counts)
# save segment
self._load_segments(dataset, requeried_document, documents, session)
self._load_segments(
session=session,
dataset=dataset,
dataset_document=requeried_document,
documents=documents,
token_counts=token_counts,
)
session.commit()
# load
self._load(
index_processor=index_processor,
session=session,
dataset=dataset,
dataset_document=requeried_document,
documents=documents,
session=session,
total_tokens=total_tokens,
)
except DocumentIsPausedError:
raise DocumentIsPausedError(f"Document paused, document id: {document_id}")
@@ -225,7 +242,7 @@ class IndexingRunner:
if not dataset:
raise ValueError("no dataset found")
# get exist document_segment list and delete
# get existing document segments
document_segments = session.scalars(
select(DocumentSegment).where(
DocumentSegment.dataset_id == dataset.id,
@@ -264,15 +281,15 @@ class IndexingRunner:
child_documents.append(child_document)
document.children = child_documents
documents.append(document)
# Preserve the full document total even when only incomplete segments are re-indexed.
total_tokens = sum(document_segment.tokens for document_segment in document_segments)
# build index
index_type = requeried_document.doc_form
index_processor = IndexProcessorFactory(index_type).init_index_processor()
self._load(
index_processor=index_processor,
session=session,
dataset=dataset,
dataset_document=requeried_document,
documents=documents,
session=session,
total_tokens=total_tokens,
)
except DocumentIsPausedError:
raise DocumentIsPausedError(f"Document paused, document id: {document_id}")
@@ -601,28 +618,16 @@ class IndexingRunner:
def _load(
self,
index_processor: BaseIndexProcessor,
session: Session,
dataset: Dataset,
dataset_document: DatasetDocument,
documents: list[Document],
session: Session,
):
"""
insert index and update document/segment status to completed
"""
total_tokens: int,
) -> None:
"""Build indexes and mark the document complete using the token total computed before hash sharding."""
embedding_model_instance = None
if dataset.indexing_technique == IndexTechniqueType.HIGH_QUALITY:
embedding_model_instance = self._get_model_manager(dataset.tenant_id).get_model_instance(
tenant_id=dataset.tenant_id,
provider=dataset.embedding_model_provider,
model_type=ModelType.TEXT_EMBEDDING,
model=dataset.embedding_model,
)
# chunk nodes by chunk size
# Build indexes using the existing hash-based worker groups.
indexing_start_at = time.perf_counter()
tokens = 0
create_keyword_thread = None
if (
dataset_document.doc_form != IndexStructureType.PARENT_CHILD_INDEX
@@ -659,12 +664,11 @@ class IndexingRunner:
chunk_documents,
dataset.id,
dataset_document.id,
embedding_model_instance,
)
)
for future in futures:
tokens += future.result()
future.result()
if (
dataset_document.doc_form != IndexStructureType.PARENT_CHILD_INDEX
and dataset.indexing_technique == IndexTechniqueType.ECONOMY
@@ -679,7 +683,7 @@ class IndexingRunner:
document_id=dataset_document.id,
after_indexing_status=IndexingStatus.COMPLETED,
extra_update_params={
DatasetDocument.tokens: tokens,
DatasetDocument.tokens: total_tokens,
DatasetDocument.completed_at: naive_utc_now(),
DatasetDocument.indexing_latency: indexing_end_at - indexing_start_at,
DatasetDocument.error: None,
@@ -720,8 +724,7 @@ class IndexingRunner:
chunk_documents: list[Document],
dataset_id: str,
dataset_document_id: str,
embedding_model_instance: ModelInstance | None,
):
) -> None:
with flask_app.app_context():
with session_factory.create_session() as session:
dataset = session.get(Dataset, dataset_id)
@@ -735,11 +738,6 @@ class IndexingRunner:
# check document is paused
self._check_document_paused_status(dataset_document.id)
tokens = 0
if embedding_model_instance:
page_content_list = [document.page_content for document in chunk_documents]
tokens += sum(embedding_model_instance.get_text_embedding_num_tokens(page_content_list))
multimodal_documents = []
for document in chunk_documents:
if document.attachments and dataset.is_multimodal:
@@ -773,8 +771,6 @@ class IndexingRunner:
session.commit()
return tokens
@staticmethod
def _check_document_paused_status(document_id: str):
indexing_cache_key = f"document_{document_id}_is_paused"
@@ -864,8 +860,14 @@ class IndexingRunner:
return documents
def _load_segments(
self, dataset: Dataset, dataset_document: DatasetDocument, documents: list[Document], session: Session
):
self,
session: Session,
dataset: Dataset,
dataset_document: DatasetDocument,
documents: list[Document],
token_counts: list[int],
) -> None:
"""Persist transformed documents and their precomputed token counts before indexing starts."""
# save node to document segment
doc_store = DatasetDocumentStore(
dataset=dataset, user_id=dataset_document.created_by, document_id=dataset_document.id
@@ -873,9 +875,10 @@ class IndexingRunner:
# add document segments
doc_store.add_documents(
session=session,
docs=documents,
save_child=dataset_document.doc_form == IndexStructureType.PARENT_CHILD_INDEX,
session=session,
token_counts=token_counts,
)
# update document status to indexing
@@ -900,7 +903,6 @@ class IndexingRunner:
DocumentSegment.indexing_at: naive_utc_now(),
},
)
pass
class DocumentIsPausedError(Exception):
+34 -2
View File
@@ -6,9 +6,21 @@ using Python's contextvars for thread-safe and async-safe storage.
import uuid
from contextvars import ContextVar
from typing import NamedTuple
class IdentityContext(NamedTuple):
"""Immutable identity values captured for logging."""
tenant_id: str
user_id: str
user_type: str
_request_id: ContextVar[str] = ContextVar("log_request_id", default="")
_trace_id: ContextVar[str] = ContextVar("log_trace_id", default="")
_EMPTY_IDENTITY_CONTEXT = IdentityContext(tenant_id="", user_id="", user_type="")
_identity: ContextVar[IdentityContext] = ContextVar("log_identity", default=_EMPTY_IDENTITY_CONTEXT)
def get_request_id() -> str:
@@ -21,15 +33,35 @@ def get_trace_id() -> str:
return _trace_id.get()
def get_identity_context() -> IdentityContext:
"""Get the immutable tenant, user, and user-type snapshot for logging."""
return _identity.get()
def set_identity_context(
*, tenant_id: str | None = None, user_id: str | None = None, user_type: str | None = None
) -> None:
"""Set primitive identity values already resolved by an authentication boundary."""
_identity.set(
IdentityContext(
tenant_id=tenant_id or "",
user_id=user_id or "",
user_type=user_type or "",
)
)
def init_request_context() -> None:
"""Initialize request context. Call at start of each request."""
"""Initialize request context and discard identity left by earlier work."""
req_id = uuid.uuid4().hex[:10]
trace_id = uuid.uuid5(uuid.NAMESPACE_DNS, req_id).hex
_request_id.set(req_id)
_trace_id.set(trace_id)
_identity.set(_EMPTY_IDENTITY_CONTEXT)
def clear_request_context() -> None:
"""Clear request context. Call at end of request (optional)."""
"""Clear request context at a request or task lifecycle boundary."""
_request_id.set("")
_trace_id.set("")
_identity.set(_EMPTY_IDENTITY_CONTEXT)
+9 -45
View File
@@ -4,10 +4,7 @@ import contextlib
import logging
from typing import override
import flask
from core.logging.context import get_request_id, get_trace_id
from core.logging.structured_formatter import IdentityDict
from core.logging.context import get_identity_context, get_request_id, get_trace_id
class TraceContextFilter(logging.Filter):
@@ -51,49 +48,16 @@ class TraceContextFilter(logging.Filter):
class IdentityContextFilter(logging.Filter):
"""
Filter that adds user identity context to log records.
Extracts tenant_id, user_id, and user_type from Flask-Login current_user.
"""Add an identity snapshot without invoking authentication or database work.
Logging can run while other libraries hold internal locks, so this filter must
only read primitive ContextVar values populated by authentication boundaries.
"""
@override
def filter(self, record: logging.LogRecord) -> bool:
identity = self._extract_identity()
record.tenant_id = identity.get("tenant_id", "")
record.user_id = identity.get("user_id", "")
record.user_type = identity.get("user_type", "")
identity = get_identity_context()
record.tenant_id = identity.tenant_id
record.user_id = identity.user_id
record.user_type = identity.user_type
return True
def _extract_identity(self) -> IdentityDict:
"""Extract identity from current_user if in request context."""
try:
if not flask.has_request_context():
return {}
from flask_login import current_user
# Check if user is authenticated using the proxy
if not current_user.is_authenticated:
return {}
# Access the underlying user object
user = current_user
from models import Account
from models.model import EndUser
identity: IdentityDict = {}
match user:
case Account():
if user.current_tenant_id:
identity["tenant_id"] = user.current_tenant_id
identity["user_id"] = user.id
identity["user_type"] = "account"
case EndUser():
identity["tenant_id"] = user.tenant_id
identity["user_id"] = user.id
identity["user_type"] = user.type or "end_user"
return identity
except Exception:
return {}
+14 -1
View File
@@ -1,7 +1,7 @@
import inspect
import json
import logging
from collections.abc import Callable, Generator
from collections.abc import Callable, Generator, Mapping
from typing import Any, cast
from urllib.parse import unquote
@@ -23,6 +23,7 @@ from core.plugin.impl.exc import (
PluginLLMPollingUnsupportedError,
PluginNotFoundError,
PluginPermissionDeniedError,
PluginRuntimeError,
PluginUniqueIdentifierError,
)
from core.trigger.errors import (
@@ -375,6 +376,18 @@ class BasePluginClient:
# type `PluginLLMPollingUnsupportedError`.
case PluginLLMPollingUnsupportedError.__name__:
raise PluginLLMPollingUnsupportedError(description=error_object.get("message"))
case PluginRuntimeError.__name__:
args = error_object.get("args")
lambda_request_id = args.get("request_id") if isinstance(args, Mapping) else None
if not isinstance(lambda_request_id, str):
lambda_request_id = None
runtime_message = error_object.get("message")
if not isinstance(runtime_message, str):
runtime_message = "Plugin runtime request failed"
raise PluginRuntimeError(
description=runtime_message,
lambda_request_id=lambda_request_id,
)
case _:
raise PluginInvokeError(description=message)
case PluginDaemonInternalServerError.__name__:
+12
View File
@@ -49,6 +49,18 @@ class PluginDaemonBadRequestError(PluginDaemonClientSideError):
description: str = "Bad Request"
class PluginRuntimeError(PluginDaemonInternalError):
"""A plugin runtime failed before it could return a valid plugin response."""
lambda_request_id: str | None
def __init__(self, description: str, lambda_request_id: str | None = None) -> None:
self.lambda_request_id = lambda_request_id
if lambda_request_id:
description = description.replace(f"RequestId: {lambda_request_id} Error: ", "", 1)
super().__init__(description)
class PluginInvokeError(PluginDaemonClientSideError, ValueError):
description: str = "Invoke Error"
+6 -21
View File
@@ -6,10 +6,7 @@ from typing import Any
from sqlalchemy import delete, func, select
from sqlalchemy.orm import Session
from core.model_manager import ModelManager
from core.rag.index_processor.constant.index_type import IndexTechniqueType
from core.rag.models.document import AttachmentDocument, Document
from graphon.model_runtime.entities.model_entities import ModelType
from models.dataset import ChildChunk, Dataset, DocumentSegment, SegmentAttachmentBinding
from models.enums import SegmentType
@@ -69,34 +66,22 @@ class DatasetDocumentStore:
def add_documents(
self,
docs: Sequence[Document],
session: Session,
docs: Sequence[Document],
token_counts: list[int],
allow_update: bool = True,
save_child: bool = False,
):
) -> None:
document_token_pairs = list(zip(docs, token_counts, strict=True))
max_position = session.scalar(
select(func.max(DocumentSegment.position)).where(DocumentSegment.document_id == self._document_id)
)
if max_position is None:
max_position = 0
embedding_model = None
if self._dataset.indexing_technique == IndexTechniqueType.HIGH_QUALITY:
model_manager = ModelManager.for_tenant(tenant_id=self._dataset.tenant_id)
embedding_model = model_manager.get_model_instance(
tenant_id=self._dataset.tenant_id,
provider=self._dataset.embedding_model_provider,
model_type=ModelType.TEXT_EMBEDDING,
model=self._dataset.embedding_model,
)
if embedding_model:
page_content_list = [doc.page_content for doc in docs]
tokens_list = embedding_model.get_text_embedding_num_tokens(page_content_list)
else:
tokens_list = [0] * len(docs)
for doc, tokens in zip(docs, tokens_list):
for doc, tokens in document_token_pairs:
if not isinstance(doc, Document):
raise ValueError("doc must be a Document")
+25
View File
@@ -0,0 +1,25 @@
"""Token counting for document segments."""
from core.model_manager import ModelManager
from core.rag.index_processor.constant.index_type import IndexTechniqueType
from core.rag.models.document import Document
from graphon.model_runtime.entities.model_entities import ModelType
from models.dataset import Dataset
def calculate_segment_token_counts(dataset: Dataset, documents: list[Document]) -> list[int]:
"""Return one token count per document, invoking the embedding model only for high-quality indexes."""
if not documents:
return []
if dataset.indexing_technique != IndexTechniqueType.HIGH_QUALITY:
return [0] * len(documents)
model_manager = ModelManager.for_tenant(tenant_id=dataset.tenant_id)
embedding_model = model_manager.get_model_instance(
tenant_id=dataset.tenant_id,
provider=dataset.embedding_model_provider,
model_type=ModelType.TEXT_EMBEDDING,
model=dataset.embedding_model,
)
return embedding_model.get_text_embedding_num_tokens([document.page_content for document in documents])
@@ -19,6 +19,7 @@ from core.rag.cleaner.clean_processor import CleanProcessor
from core.rag.datasource.keyword.keyword_factory import Keyword
from core.rag.datasource.vdb.vector_factory import Vector
from core.rag.docstore.dataset_docstore import DatasetDocumentStore
from core.rag.embedding.token_counter import calculate_segment_token_counts
from core.rag.entities import Rule
from core.rag.extractor.entity.extract_setting import ExtractSetting
from core.rag.extractor.extract_processor import ExtractProcessor
@@ -244,10 +245,16 @@ class ParagraphIndexProcessor(BaseIndexProcessor):
all_multimodal_documents.extend(doc.attachments)
documents.append(doc)
if documents:
token_counts = calculate_segment_token_counts(dataset=dataset, documents=documents)
# save node to document segment
doc_store = DatasetDocumentStore(dataset=dataset, user_id=document.created_by, document_id=document.id)
# add document segments
doc_store.add_documents(docs=documents, save_child=False, session=session)
doc_store.add_documents(
session=session,
docs=documents,
token_counts=token_counts,
save_child=False,
)
session.commit()
if dataset.indexing_technique == IndexTechniqueType.HIGH_QUALITY:
vector = Vector(dataset, session=session)
@@ -15,6 +15,7 @@ from core.model_manager import ModelInstance
from core.rag.cleaner.clean_processor import CleanProcessor
from core.rag.datasource.vdb.vector_factory import Vector
from core.rag.docstore.dataset_docstore import DatasetDocumentStore
from core.rag.embedding.token_counter import calculate_segment_token_counts
from core.rag.entities import ParentMode, Rule
from core.rag.extractor.entity.extract_setting import ExtractSetting
from core.rag.extractor.extract_processor import ExtractProcessor
@@ -304,6 +305,7 @@ class ParentChildIndexProcessor(BaseIndexProcessor):
doc.attachments = self._get_content_files(doc, current_user=account, session=session)
documents.append(doc)
if documents:
token_counts = calculate_segment_token_counts(dataset=dataset, documents=documents)
# update document parent mode
dataset_process_rule = DatasetProcessRule(
dataset_id=dataset.id,
@@ -321,7 +323,12 @@ class ParentChildIndexProcessor(BaseIndexProcessor):
# save node to document segment
doc_store = DatasetDocumentStore(dataset=dataset, user_id=document.created_by, document_id=document.id)
# add document segments
doc_store.add_documents(docs=documents, save_child=True, session=session)
doc_store.add_documents(
session=session,
docs=documents,
token_counts=token_counts,
save_child=True,
)
session.commit()
if dataset.indexing_technique == IndexTechniqueType.HIGH_QUALITY:
all_child_documents = []
@@ -17,6 +17,7 @@ from core.llm_generator.llm_generator import LLMGenerator
from core.rag.cleaner.clean_processor import CleanProcessor
from core.rag.datasource.vdb.vector_factory import Vector
from core.rag.docstore.dataset_docstore import DatasetDocumentStore
from core.rag.embedding.token_counter import calculate_segment_token_counts
from core.rag.entities import Rule
from core.rag.extractor.entity.extract_setting import ExtractSetting
from core.rag.extractor.extract_processor import ExtractProcessor
@@ -205,9 +206,15 @@ class QAIndexProcessor(BaseIndexProcessor):
doc = Document(page_content=qa_chunk.question, metadata=metadata)
documents.append(doc)
if documents:
token_counts = calculate_segment_token_counts(dataset=dataset, documents=documents)
# save node to document segment
doc_store = DatasetDocumentStore(dataset=dataset, user_id=document.created_by, document_id=document.id)
doc_store.add_documents(docs=documents, save_child=False, session=session)
doc_store.add_documents(
session=session,
docs=documents,
token_counts=token_counts,
save_child=False,
)
session.commit()
if dataset.indexing_technique == IndexTechniqueType.HIGH_QUALITY:
vector = Vector(dataset, session=session)
+1
View File
@@ -61,6 +61,7 @@ class RBACPermission(StrEnum):
WORKSPACE_ROLE_MANAGE = "workspace_role_manage"
API_EXTENSION_MANAGE = "api_extension_manage"
CUSTOMIZATION_MANAGE = "customization_manage"
AGENT_MANAGE = "agent_manage"
SNIPPETS_CREATE_AND_MODIFY = "snippets_create_and_modify"
SNIPPETS_MANAGE = "snippets_management"
+36 -15
View File
@@ -17,6 +17,7 @@ from core.tools.entities.tool_entities import (
ToolParameter,
ToolProviderType,
)
from core.tools.entities.ui_entities import ToolUIMessage
class Tool(ABC):
@@ -58,7 +59,6 @@ class Tool(ABC):
if self.runtime and self.runtime.runtime_parameters:
tool_parameters.update(self.runtime.runtime_parameters)
# try parse tool parameters into the correct type
tool_parameters = self._transform_tool_parameters_type(tool_parameters)
result = self._invoke(
@@ -87,14 +87,14 @@ class Tool(ABC):
return result
def _transform_tool_parameters_type(self, tool_parameters: dict[str, Any]) -> dict[str, Any]:
"""
Transform tool parameters type
"""
# Temp fix for the issue that the tool parameters will be converted to empty while validating the credentials
"""Transform declared tool parameter values without resolving runtime schemas."""
result = deepcopy(tool_parameters)
for parameter in self.entity.parameters or []:
if parameter.name in tool_parameters:
result[parameter.name] = parameter.type.cast_value(tool_parameters[parameter.name])
if parameter.multiple:
result[parameter.name] = parameter.init_frontend_parameter(result.get(parameter.name))
else:
result[parameter.name] = parameter.type.cast_value(tool_parameters[parameter.name])
return result
@@ -196,17 +196,31 @@ class Tool(ABC):
}:
continue
parameter_schema: dict[str, Any] = (
{
"type": parameter.type.as_normal_type(),
"description": parameter.llm_description or "",
}
if parameter.input_schema is None
else deepcopy(parameter.input_schema)
)
is_multiple_select = parameter.multiple and parameter.type in {
ToolParameter.ToolParameterType.SELECT,
ToolParameter.ToolParameterType.DYNAMIC_SELECT,
}
if is_multiple_select:
item_schema: dict[str, Any] = {"type": "string"}
if parameter.type == ToolParameter.ToolParameterType.SELECT and parameter.options:
item_schema["enum"] = [option.value for option in parameter.options]
parameter_schema: dict[str, Any] = {"type": "array", "items": item_schema}
else:
parameter_schema = (
{
"type": parameter.type.as_normal_type(),
"description": parameter.llm_description or "",
}
if parameter.input_schema is None
else deepcopy(parameter.input_schema)
)
parameter_schema.setdefault("description", parameter.llm_description or "")
if parameter.type == ToolParameter.ToolParameterType.SELECT and parameter.options:
if (
not is_multiple_select
and parameter.type == ToolParameter.ToolParameterType.SELECT
and parameter.options
):
parameter_schema["enum"] = [option.value for option in parameter.options]
schema["properties"][parameter.name] = parameter_schema
@@ -282,6 +296,13 @@ class Tool(ABC):
message=ToolInvokeMessage.JsonMessage(json_object=object, suppress_output=suppress_output),
)
def create_ui_message(self, ui_message: ToolUIMessage | dict[str, Any]) -> ToolInvokeMessage:
"""Create a validated, model-invisible UI message for chat clients."""
return ToolInvokeMessage(
type=ToolInvokeMessage.MessageType.UI,
message=ToolUIMessage.model_validate(ui_message),
)
def create_variable_message(
self, variable_name: str, variable_value: Any, stream: bool = False
) -> ToolInvokeMessage:
@@ -7,6 +7,9 @@ from sqlalchemy.orm import Session
from core.tools.builtin_tool.tool import BuiltinTool
from core.tools.entities.tool_entities import ToolInvokeMessage
from core.tools.entities.ui_entities import A2UI_CATALOG_ID, A2UI_PROTOCOL_VERSION
_CURRENT_TIME_SURFACE_ID = "current-time"
class CurrentTimeTool(BuiltinTool):
@@ -20,19 +23,60 @@ class CurrentTimeTool(BuiltinTool):
app_id: str | None = None,
message_id: str | None = None,
) -> Generator[ToolInvokeMessage, None, None]:
"""
invoke tools
"""
# get timezone
tz = tool_parameters.get("timezone", "UTC")
fm = tool_parameters.get("format") or "%Y-%m-%d %H:%M:%S %Z"
if tz == "UTC":
yield self.create_text_message(f"{datetime.now(UTC).strftime(fm)}")
return
"""Return the formatted time for the model and a standard time card for chat clients.
try:
tz = pytz_timezone(tz)
except Exception:
yield self.create_text_message(f"Invalid timezone: {tz}")
return
yield self.create_text_message(f"{datetime.now(tz).strftime(fm)}")
Invalid timezone values retain the existing text-only error response.
"""
timezone_name = tool_parameters.get("timezone", "UTC")
fm = tool_parameters.get("format") or "%Y-%m-%d %H:%M:%S %Z"
if timezone_name == "UTC":
current_time = datetime.now(UTC)
else:
try:
timezone_info = pytz_timezone(timezone_name)
except Exception:
yield self.create_text_message(f"Invalid timezone: {timezone_name}")
return
current_time = datetime.now(timezone_info)
formatted_time = current_time.strftime(fm)
yield self.create_text_message(formatted_time)
yield self.create_ui_message(
{
"messages": [
{
"version": A2UI_PROTOCOL_VERSION,
"createSurface": {
"surfaceId": _CURRENT_TIME_SURFACE_ID,
"catalogId": A2UI_CATALOG_ID,
},
},
{
"version": A2UI_PROTOCOL_VERSION,
"updateDataModel": {
"surfaceId": _CURRENT_TIME_SURFACE_ID,
"value": {"currentTime": current_time.isoformat()},
},
},
{
"version": A2UI_PROTOCOL_VERSION,
"updateComponents": {
"surfaceId": _CURRENT_TIME_SURFACE_ID,
"components": [
{
"id": "root",
"component": "Card",
"children": ["time"],
},
{
"id": "time",
"component": "DateTime",
"value": {"path": "/currentTime"},
"format": "datetime",
},
],
},
},
],
}
)
+42 -6
View File
@@ -32,6 +32,7 @@ from core.plugin.entities.parameters import (
from core.rag.entities import RetrievalSourceMetadata
from core.tools.entities.common_entities import I18nObject
from core.tools.entities.constants import TOOL_SELECTOR_MODEL_IDENTITY
from core.tools.entities.ui_entities import ToolUIMessage
class EmojiIconDict(TypedDict):
@@ -240,13 +241,15 @@ class ToolInvokeMessage(BaseModel):
LOG = auto()
BLOB_CHUNK = auto()
RETRIEVER_RESOURCES = auto()
UI = auto()
type: MessageType = MessageType.TEXT
"""
plain text, image url or link url
"""
message: (
JsonMessage
ToolUIMessage
| JsonMessage
| TextMessage
| BlobChunkMessage
| BlobMessage
@@ -275,6 +278,8 @@ class ToolInvokeMessage(BaseModel):
v = {"json_object": v}
elif msg_type == cls.MessageType.FILE:
v = {"file_marker": "file_marker"}
elif msg_type == cls.MessageType.UI:
v = ToolUIMessage.model_validate(v)
return v
@@ -292,9 +297,7 @@ class ToolInvokeMessageBinary(BaseModel):
class ToolParameter(PluginParameter):
"""
Overrides type
"""
"""Tool-specific parameter declaration and invocation-value normalization."""
class ToolParameterType(StrEnum):
"""
@@ -333,12 +336,28 @@ class ToolParameter(PluginParameter):
LLM = auto() # will be set by LLM
type: ToolParameterType = Field(..., description="The type of the parameter")
multiple: bool = Field(
default=False,
description="Whether the parameter is multiple select, only valid for select or dynamic-select type",
)
human_description: I18nObject | None = Field(default=None, description="The description presented to the user")
form: ToolParameterForm = Field(..., description="The form of the parameter, schema/form/llm")
llm_description: str | None = None
# MCP object and array type parameters use this field to store the schema
input_schema: dict[str, Any] | None = None
@model_validator(mode="after")
def validate_multiple(self) -> ToolParameter:
supports_multiple = self.type in {
self.ToolParameterType.SELECT,
self.ToolParameterType.DYNAMIC_SELECT,
}
if self.multiple and not supports_multiple:
raise ValueError("multiple is only valid for select and dynamic-select parameters")
if supports_multiple and self.default is not None and (isinstance(self.default, list) != self.multiple):
raise ValueError("default must be a list exactly when multiple is true")
return self
@classmethod
def get_simple_instance(
cls,
@@ -378,8 +397,25 @@ class ToolParameter(PluginParameter):
options=option_objs,
)
def init_frontend_parameter(self, value: Any):
return init_frontend_parameter(self, self.type, value)
def init_frontend_parameter(self, value: Any) -> Any:
"""Normalize a value against this tool parameter's full declaration."""
if not self.multiple:
return init_frontend_parameter(self, self.type, value)
parameter_value = self.default if value is None else value
if parameter_value is None:
parameter_value = []
if not isinstance(parameter_value, list):
raise ValueError(f"tool parameter {self.name} must be a list when multiple is true")
if not all(isinstance(item, str) for item in parameter_value):
raise ValueError(f"tool parameter {self.name} must contain only strings")
if self.required and not parameter_value:
raise ValueError(f"tool parameter {self.name} not found in tool config")
if self.type == self.ToolParameterType.SELECT:
options = [option.value for option in self.options]
if any(item not in options for item in parameter_value):
raise ValueError(f"tool parameter {self.name} value {parameter_value} not in options {options}")
return parameter_value
class ToolProviderIdentity(BaseModel):
+675
View File
@@ -0,0 +1,675 @@
"""Validated, read-only UI messages emitted by tools.
The public wire format is the A2UI v0.9.1 flat message shape, narrowed to a
Dify-owned catalog. Tool authors can bind display values to the surface data
model, but cannot supply executable actions, HTML, styles, themes, or custom
components. A complete ``ToolUIMessage`` describes exactly one surface and is
validated as a bounded, self-contained component graph before it crosses into
chat streaming. Sequential data-model patches are materialized with the same
object/array upsert semantics as the web renderer so cumulative limits cannot
be bypassed with individually small updates.
"""
from __future__ import annotations
import json
import re
import uuid
from collections.abc import Sequence
from enum import StrEnum
from typing import Annotated, Literal
from pydantic import (
BaseModel,
ConfigDict,
Field,
JsonValue,
SerializerFunctionWrapHandler,
field_validator,
model_serializer,
model_validator,
)
A2UI_PROTOCOL = "a2ui"
A2UI_PROTOCOL_VERSION = "v0.9.1"
A2UI_CATALOG_ID = "https://dify.ai/a2ui/catalog/v1"
DIFY_UI_JSON_ENVELOPE_KEY = "__dify_ui__"
MAX_UI_MESSAGES = 64
MAX_UI_COMPONENTS = 100
MAX_UI_STRING_LENGTH = 4096
MAX_UI_PAYLOAD_BYTES = 128 * 1024
MAX_DATA_MODEL_DEPTH = 16
MAX_DATA_MODEL_NODES = 2000
MAX_DATA_MODEL_ARRAY_INDEX = 1000
MAX_JSON_POINTER_SEGMENTS = 16
MAX_UI_PARTS_PER_MESSAGE = 16
MAX_UI_PARTS_PAYLOAD_BYTES = 512 * 1024
_ID_PATTERN = re.compile(r"^[A-Za-z0-9][A-Za-z0-9_.:-]{0,127}$")
_ARRAY_INDEX_PATTERN = re.compile(r"^(?:0|[1-9]\d*)$")
_DANGEROUS_POINTER_SEGMENTS = {"__proto__", "constructor", "prototype"}
_DANGEROUS_DATA_KEYS = _DANGEROUS_POINTER_SEGMENTS
_MAX_HISTORY_UI_PART_CANDIDATES = MAX_UI_PARTS_PER_MESSAGE * 4
_UI_PART_ID_NAMESPACE = uuid.uuid5(uuid.NAMESPACE_URL, "https://dify.ai/a2ui/part-id/v1")
class _StrictModel(BaseModel):
model_config = ConfigDict(
extra="forbid",
populate_by_name=True,
serialize_by_alias=True,
allow_inf_nan=False,
)
class A2UIDataBinding(_StrictModel):
"""A JSON Pointer into the surface data model."""
path: str
@field_validator("path")
@classmethod
def _validate_path(cls, value: str) -> str:
return _validate_json_pointer(value, label="data binding path")
type DynamicString = str | A2UIDataBinding
type DynamicNumber = int | float | A2UIDataBinding
type DynamicScalar = str | int | float | bool | None | A2UIDataBinding
class A2UIComponentType(StrEnum):
CARD = "Card"
ROW = "Row"
COLUMN = "Column"
TEXT = "Text"
ICON = "Icon"
DIVIDER = "Divider"
BADGE = "Badge"
METRIC = "Metric"
DATE_TIME = "DateTime"
PROGRESS = "Progress"
KEY_VALUE = "KeyValue"
class A2UIComponent(_StrictModel):
"""One flat component entry from the Dify catalog."""
id: str
component: A2UIComponentType
children: list[str] | None = None
title: DynamicString | None = None
gap: Literal["small", "medium", "large"] | None = None
align: Literal["start", "center", "end"] | None = None
text: DynamicString | None = None
variant: Literal["body", "caption"] | None = None
name: (
Literal[
"clock",
"cloud",
"sun",
"rain",
"snow",
"wind",
"thermometer",
"calendar",
"location",
]
| None
) = None
tone: Literal["neutral", "info", "success", "warning", "critical"] | None = None
label: DynamicString | None = None
value: DynamicScalar | None = None
unit: DynamicString | None = None
format: Literal["date", "time", "datetime"] | None = None
max: DynamicNumber | None = None
@field_validator("id")
@classmethod
def _validate_id(cls, value: str) -> str:
if not _ID_PATTERN.fullmatch(value):
raise ValueError("component id contains unsupported characters or is too long")
return value
@field_validator("children")
@classmethod
def _validate_children(cls, value: list[str] | None) -> list[str] | None:
if value is None:
return None
if len(value) > MAX_UI_COMPONENTS:
raise ValueError("component has too many children")
if len(value) != len(set(value)):
raise ValueError("component children must not contain duplicate ids")
for child_id in value:
if not _ID_PATTERN.fullmatch(child_id):
raise ValueError("child component id contains unsupported characters or is too long")
return value
@model_validator(mode="after")
def _validate_component_props(self) -> A2UIComponent:
present = self.model_fields_set - {"id", "component"}
allowed: dict[A2UIComponentType, set[str]] = {
A2UIComponentType.CARD: {"children", "title"},
A2UIComponentType.ROW: {"children", "gap", "align"},
A2UIComponentType.COLUMN: {"children", "gap"},
A2UIComponentType.TEXT: {"text", "variant"},
A2UIComponentType.ICON: {"name"},
A2UIComponentType.DIVIDER: set(),
A2UIComponentType.BADGE: {"text", "tone"},
A2UIComponentType.METRIC: {"label", "value", "unit"},
A2UIComponentType.DATE_TIME: {"value", "format"},
A2UIComponentType.PROGRESS: {"value", "max", "label"},
A2UIComponentType.KEY_VALUE: {"label", "value"},
}
required: dict[A2UIComponentType, set[str]] = {
A2UIComponentType.CARD: {"children"},
A2UIComponentType.ROW: {"children"},
A2UIComponentType.COLUMN: {"children"},
A2UIComponentType.TEXT: {"text"},
A2UIComponentType.ICON: {"name"},
A2UIComponentType.DIVIDER: set(),
A2UIComponentType.BADGE: {"text"},
A2UIComponentType.METRIC: {"label", "value"},
A2UIComponentType.DATE_TIME: {"value"},
A2UIComponentType.PROGRESS: {"value", "label"},
A2UIComponentType.KEY_VALUE: {"label", "value"},
}
unexpected = present - allowed[self.component]
missing = required[self.component] - present
if unexpected:
raise ValueError(f"{self.component} does not support properties: {sorted(unexpected)}")
if missing:
raise ValueError(f"{self.component} requires properties: {sorted(missing)}")
nullable_props = (
{"value"} if self.component in {A2UIComponentType.METRIC, A2UIComponentType.KEY_VALUE} else set()
)
null_props = {prop for prop in present if getattr(self, prop) is None and prop not in nullable_props}
if null_props:
raise ValueError(f"{self.component} properties cannot be null: {sorted(null_props)}")
if self.component == A2UIComponentType.DATE_TIME and not isinstance(self.value, str | A2UIDataBinding):
raise ValueError("DateTime value must be a string or data binding")
if self.component == A2UIComponentType.PROGRESS and (
isinstance(self.value, bool) or not isinstance(self.value, int | float | A2UIDataBinding)
):
raise ValueError("Progress value must be a number or data binding")
if (
self.component == A2UIComponentType.PROGRESS
and "max" in present
and (isinstance(self.max, bool) or not isinstance(self.max, int | float | A2UIDataBinding))
):
raise ValueError("Progress max must be a number or data binding")
return self
@model_serializer(mode="wrap")
def _serialize_component(self, handler: SerializerFunctionWrapHandler) -> dict[str, JsonValue]:
serialized = handler(self)
return {
key: value
for key, value in serialized.items()
if key in {"id", "component"} or key in self.model_fields_set
}
class A2UICreateSurface(_StrictModel):
surface_id: str = Field(alias="surfaceId")
catalog_id: Literal["https://dify.ai/a2ui/catalog/v1"] = Field(alias="catalogId")
@field_validator("surface_id")
@classmethod
def _validate_surface_id(cls, value: str) -> str:
if not _ID_PATTERN.fullmatch(value):
raise ValueError("surface id contains unsupported characters or is too long")
return value
class A2UIUpdateComponents(_StrictModel):
surface_id: str = Field(alias="surfaceId")
components: Annotated[list[A2UIComponent], Field(min_length=1, max_length=MAX_UI_COMPONENTS)]
@field_validator("surface_id")
@classmethod
def _validate_surface_id(cls, value: str) -> str:
if not _ID_PATTERN.fullmatch(value):
raise ValueError("surface id contains unsupported characters or is too long")
return value
@field_validator("components")
@classmethod
def _validate_unique_component_ids(cls, value: list[A2UIComponent]) -> list[A2UIComponent]:
ids = [component.id for component in value]
if len(ids) != len(set(ids)):
raise ValueError("updateComponents contains duplicate component ids")
return value
class A2UIUpdateDataModel(_StrictModel):
surface_id: str = Field(alias="surfaceId")
value: JsonValue
path: str | None = None
@field_validator("surface_id")
@classmethod
def _validate_surface_id(cls, value: str) -> str:
if not _ID_PATTERN.fullmatch(value):
raise ValueError("surface id contains unsupported characters or is too long")
return value
@field_validator("value")
@classmethod
def _validate_value(cls, value: JsonValue) -> JsonValue:
_validate_data_model_value(value)
return value
@field_validator("path")
@classmethod
def _validate_path(cls, value: str | None) -> str | None:
if value is None:
return value
return _validate_json_pointer(value, label="data model path", enforce_array_index_limit=True)
@model_serializer(mode="wrap")
def _serialize_update(self, handler: SerializerFunctionWrapHandler) -> dict[str, JsonValue]:
serialized = handler(self)
if "path" not in self.model_fields_set:
serialized.pop("path", None)
return serialized
class A2UIDeleteSurface(_StrictModel):
surface_id: str = Field(alias="surfaceId")
@field_validator("surface_id")
@classmethod
def _validate_surface_id(cls, value: str) -> str:
if not _ID_PATTERN.fullmatch(value):
raise ValueError("surface id contains unsupported characters or is too long")
return value
class A2UIMessage(_StrictModel):
"""A single A2UI v0.9.1 server message."""
version: Literal["v0.9.1"]
create_surface: A2UICreateSurface | None = Field(default=None, alias="createSurface")
update_components: A2UIUpdateComponents | None = Field(default=None, alias="updateComponents")
update_data_model: A2UIUpdateDataModel | None = Field(default=None, alias="updateDataModel")
delete_surface: A2UIDeleteSurface | None = Field(default=None, alias="deleteSurface")
@model_validator(mode="after")
def _validate_exactly_one_operation(self) -> A2UIMessage:
operations = (
self.create_surface,
self.update_components,
self.update_data_model,
self.delete_surface,
)
if sum(operation is not None for operation in operations) != 1:
raise ValueError("A2UI message must contain exactly one operation")
return self
@model_serializer(mode="wrap")
def _serialize_message(self, handler: SerializerFunctionWrapHandler) -> dict[str, JsonValue]:
return {key: value for key, value in handler(self).items() if value is not None}
@property
def surface_id(self) -> str:
operation = self.create_surface or self.update_components or self.update_data_model or self.delete_surface
assert operation is not None
return operation.surface_id
class ToolUIMessage(_StrictModel):
"""A complete, validated UI surface emitted by one tool result.
Validation covers both the component graph and every materialized
data-model revision, because clients render the message sequence in order.
"""
protocol: Literal["a2ui"] = "a2ui"
protocol_version: Literal["v0.9.1"] = "v0.9.1"
messages: Annotated[list[A2UIMessage], Field(min_length=1, max_length=MAX_UI_MESSAGES)]
fallback: str | None = None
@field_validator("fallback")
@classmethod
def _validate_fallback(cls, value: str | None) -> str | None:
if value is not None and len(value) > MAX_UI_STRING_LENGTH:
raise ValueError("UI fallback is too long")
return value
@model_validator(mode="after")
def _validate_surface(self) -> ToolUIMessage:
first = self.messages[0]
if first.create_surface is None:
raise ValueError("first A2UI message must be createSurface")
if any(message.create_surface is not None for message in self.messages[1:]):
raise ValueError("createSurface may only appear as the first message")
delete_indexes = [index for index, message in enumerate(self.messages) if message.delete_surface]
if delete_indexes and delete_indexes != [len(self.messages) - 1]:
raise ValueError("deleteSurface may only appear once as the final message")
surface_id = first.surface_id
if any(message.surface_id != surface_id for message in self.messages):
raise ValueError("all A2UI messages in a tool UI message must target the same surface")
components: dict[str, A2UIComponent] = {}
data_model: JsonValue = {}
root_seen_before_delete = False
for message in self.messages[1:]:
if message.update_components is not None:
for component in message.update_components.components:
components[component.id] = component
if len(components) > MAX_UI_COMPONENTS:
raise ValueError("UI surface has too many components")
if message.update_data_model is not None:
data_model = _apply_data_model_update(data_model, message.update_data_model)
_validate_data_model_value(data_model)
if message.delete_surface is not None:
root_seen_before_delete = "root" in components
if "root" not in components and not root_seen_before_delete:
raise ValueError("UI surface must define a component with id 'root'")
_validate_component_graph(components)
payload = self.model_dump(mode="json", by_alias=True, exclude_none=True)
_validate_bounded_json(payload)
return self
@model_serializer(mode="wrap")
def _serialize_ui_message(self, handler: SerializerFunctionWrapHandler) -> dict[str, JsonValue]:
return {key: value for key, value in handler(self).items() if value is not None}
@property
def surface_id(self) -> str:
return self.messages[0].surface_id
class MessageUIPart(_StrictModel):
"""SSE/history representation of one tool-owned UI surface revision."""
part_id: Annotated[str, Field(min_length=1, max_length=512)]
sequence: Annotated[int, Field(ge=1)]
protocol: Literal["a2ui"] = "a2ui"
protocol_version: Literal["v0.9.1"] = "v0.9.1"
messages: Annotated[list[A2UIMessage], Field(min_length=1, max_length=MAX_UI_MESSAGES)]
fallback: str | None = None
@model_validator(mode="after")
def _validate_messages(self) -> MessageUIPart:
ToolUIMessage(
protocol=self.protocol,
protocol_version=self.protocol_version,
messages=self.messages,
fallback=self.fallback,
)
return self
@model_serializer(mode="wrap")
def _serialize_part(self, handler: SerializerFunctionWrapHandler) -> dict[str, JsonValue]:
return {key: value for key, value in handler(self).items() if value is not None}
@classmethod
def from_tool_ui_message(
cls,
*,
part_id: str,
sequence: int,
ui_message: ToolUIMessage,
) -> MessageUIPart:
return cls(
part_id=part_id,
sequence=sequence,
protocol=ui_message.protocol,
protocol_version=ui_message.protocol_version,
messages=ui_message.messages,
fallback=ui_message.fallback,
)
def extract_ui_message_from_json(value: JsonValue) -> ToolUIMessage | None:
"""Recognize the reserved compatibility envelope used by older SDKs."""
if not isinstance(value, dict) or set(value) != {DIFY_UI_JSON_ENVELOPE_KEY}:
return None
return ToolUIMessage.model_validate(value[DIFY_UI_JSON_ENVELOPE_KEY])
def parse_tool_ui_messages(value: object) -> list[ToolUIMessage]:
"""Validate a list received through the Agent backend metadata channel."""
if not isinstance(value, list):
raise ValueError("dify_ui_messages metadata must be a list")
if len(value) > MAX_UI_PARTS_PER_MESSAGE:
raise ValueError(f"tool UI batch cannot contain more than {MAX_UI_PARTS_PER_MESSAGE} messages")
messages = [ToolUIMessage.model_validate(item) for item in value]
validate_tool_ui_message_batch(messages)
return messages
def build_ui_part_id(namespace: str, surface_id: str) -> str:
"""Build a stable, bounded ID from an unambiguous tool/surface tuple."""
if not isinstance(namespace, str) or not isinstance(surface_id, str):
raise TypeError("UI part namespace and surface id must be strings")
identity = json.dumps((namespace, surface_id), ensure_ascii=True, separators=(",", ":"))
return f"ui-{uuid.uuid5(_UI_PART_ID_NAMESPACE, identity)}"
def validate_tool_ui_message_batch(messages: Sequence[ToolUIMessage]) -> None:
"""Enforce the per-tool-call UI batch budget before queue publication."""
if len(messages) > MAX_UI_PARTS_PER_MESSAGE:
raise ValueError(f"tool UI batch cannot contain more than {MAX_UI_PARTS_PER_MESSAGE} messages")
if _serialized_model_list_size(messages) > MAX_UI_PARTS_PAYLOAD_BYTES:
raise ValueError(f"tool UI batch payload cannot exceed {MAX_UI_PARTS_PAYLOAD_BYTES} bytes")
def validate_ui_part_batch(parts: Sequence[MessageUIPart]) -> None:
"""Enforce persisted/current assistant-message UI budgets."""
if len(parts) > MAX_UI_PARTS_PER_MESSAGE:
raise ValueError(f"assistant message cannot contain more than {MAX_UI_PARTS_PER_MESSAGE} UI parts")
part_ids = [part.part_id for part in parts]
if len(part_ids) != len(set(part_ids)):
raise ValueError("assistant message UI parts must have distinct part ids")
if _serialized_model_list_size(parts) > MAX_UI_PARTS_PAYLOAD_BYTES:
raise ValueError(f"assistant message UI parts cannot exceed {MAX_UI_PARTS_PAYLOAD_BYTES} bytes")
def upsert_ui_part(parts: Sequence[MessageUIPart], part: MessageUIPart) -> list[MessageUIPart] | None:
"""Return a bounded new part list, or ``None`` for a stale revision."""
candidate = list(parts)
for index, existing_part in enumerate(candidate):
if existing_part.part_id != part.part_id:
continue
if existing_part.sequence >= part.sequence:
return None
candidate[index] = part
break
else:
candidate.append(part)
validate_ui_part_batch(candidate)
return candidate
def parse_history_ui_parts(value: object) -> list[MessageUIPart]:
"""Best-effort recovery of bounded UI parts from untrusted historical metadata."""
if not isinstance(value, list):
return []
parts: list[MessageUIPart] = []
for item in value[:_MAX_HISTORY_UI_PART_CANDIDATES]:
try:
part = MessageUIPart.model_validate(item)
updated_parts = upsert_ui_part(parts, part)
except (TypeError, ValueError):
continue
if updated_parts is not None:
parts = updated_parts
return parts
def _validate_component_graph(components: dict[str, A2UIComponent]) -> None:
for component in components.values():
for child_id in component.children or []:
if child_id not in components:
raise ValueError(f"component {component.id!r} references unknown child {child_id!r}")
visiting: set[str] = set()
visited: set[str] = set()
def visit(component_id: str) -> None:
if component_id in visiting:
raise ValueError("UI component graph contains a cycle")
if component_id in visited:
return
visiting.add(component_id)
for child_id in components[component_id].children or []:
visit(child_id)
visiting.remove(component_id)
visited.add(component_id)
for component_id in components:
visit(component_id)
parent_by_child: dict[str, str] = {}
for component in components.values():
for child_id in component.children or []:
if child_id == "root":
raise ValueError("root component cannot be referenced as a child")
existing_parent = parent_by_child.get(child_id)
if existing_parent is not None:
raise ValueError(
f"component {child_id!r} has multiple parents: {existing_parent!r} and {component.id!r}"
)
parent_by_child[child_id] = component.id
reachable = {"root"}
pending = ["root"]
while pending:
component_id = pending.pop()
for child_id in components[component_id].children or []:
if child_id in reachable:
continue
reachable.add(child_id)
pending.append(child_id)
unreachable = set(components) - reachable
if unreachable:
raise ValueError(f"UI component graph contains components unreachable from root: {sorted(unreachable)}")
def _serialized_model_list_size(values: Sequence[BaseModel]) -> int:
payload = [value.model_dump(mode="json", by_alias=True, exclude_none=True) for value in values]
return len(json.dumps(payload, ensure_ascii=False, separators=(",", ":")).encode())
def _validate_json_pointer(
value: str,
*,
label: str,
enforce_array_index_limit: bool = False,
) -> str:
if not value.startswith("/"):
raise ValueError(f"{label} must be a JSON Pointer beginning with '/'")
if len(value) > 256:
raise ValueError(f"{label} is too long")
if re.search(r"~(?![01])", value):
raise ValueError(f"{label} contains an invalid JSON Pointer escape")
decoded_segments = _decode_json_pointer(value)
if len(decoded_segments) > MAX_JSON_POINTER_SEGMENTS:
raise ValueError(f"{label} contains too many segments")
if set(decoded_segments).intersection(_DANGEROUS_POINTER_SEGMENTS):
raise ValueError(f"{label} contains a forbidden segment")
if enforce_array_index_limit and any(
segment.isdecimal() and int(segment) > MAX_DATA_MODEL_ARRAY_INDEX for segment in decoded_segments
):
raise ValueError(f"{label} contains an array index larger than {MAX_DATA_MODEL_ARRAY_INDEX}")
return value
def _decode_json_pointer(value: str) -> list[str]:
if value == "/":
return []
return [segment.replace("~1", "/").replace("~0", "~") for segment in value.split("/")[1:]]
def _apply_data_model_update(current: JsonValue, update: A2UIUpdateDataModel) -> JsonValue:
path = update.path
if path is None or path == "/":
return update.value
segments = _decode_json_pointer(path)
def apply_at(node: JsonValue | None, segment_index: int) -> JsonValue:
if segment_index == len(segments):
return update.value
segment = segments[segment_index]
is_array_segment = _ARRAY_INDEX_PATTERN.fullmatch(segment) is not None
if isinstance(node, list) or (not isinstance(node, dict) and is_array_segment):
if not is_array_segment:
raise ValueError("data model array paths must use canonical non-negative indexes")
index = int(segment)
if index > MAX_DATA_MODEL_ARRAY_INDEX:
raise ValueError(f"data model array index cannot exceed {MAX_DATA_MODEL_ARRAY_INDEX}")
next_node = list(node) if isinstance(node, list) else []
if index > len(next_node):
raise ValueError("data model array index cannot create a gap")
child = next_node[index] if index < len(next_node) else None
updated_child = apply_at(child, segment_index + 1)
if index == len(next_node):
next_node.append(updated_child)
else:
next_node[index] = updated_child
return next_node
next_node = dict(node) if isinstance(node, dict) else {}
next_node[segment] = apply_at(next_node.get(segment), segment_index + 1)
return next_node
return apply_at(current, 0)
def _validate_data_model_value(value: JsonValue) -> None:
nodes = 0
def walk(node: JsonValue, *, depth: int) -> None:
nonlocal nodes
nodes += 1
if nodes > MAX_DATA_MODEL_NODES:
raise ValueError("data model value has too many nodes")
if depth > MAX_DATA_MODEL_DEPTH:
raise ValueError("data model value is nested too deeply")
if isinstance(node, list):
for item in node:
walk(item, depth=depth + 1)
return
if isinstance(node, dict):
unsafe_keys = set(node).intersection(_DANGEROUS_DATA_KEYS)
if unsafe_keys:
raise ValueError(f"data model value contains forbidden keys: {sorted(unsafe_keys)}")
for item in node.values():
walk(item, depth=depth + 1)
walk(value, depth=0)
def _validate_bounded_json(value: JsonValue) -> None:
def walk(node: JsonValue) -> None:
if isinstance(node, str):
if len(node) > MAX_UI_STRING_LENGTH:
raise ValueError("UI payload contains a string that is too long")
return
if isinstance(node, list):
for item in node:
walk(item)
return
if isinstance(node, dict):
for item in node.values():
walk(item)
walk(value)
encoded = json.dumps(value, ensure_ascii=False, separators=(",", ":")).encode()
if len(encoded) > MAX_UI_PAYLOAD_BYTES:
raise ValueError("UI payload is too large")
+165 -8
View File
@@ -3,6 +3,7 @@ import json
import logging
from collections.abc import Generator, Iterable
from copy import deepcopy
from dataclasses import dataclass
from datetime import UTC, datetime
from mimetypes import guess_type
from typing import Any, Union, cast
@@ -21,6 +22,12 @@ from core.tools.entities.tool_entities import (
ToolInvokeMeta,
ToolParameter,
)
from core.tools.entities.ui_entities import (
DIFY_UI_JSON_ENVELOPE_KEY,
ToolUIMessage,
extract_ui_message_from_json,
validate_tool_ui_message_batch,
)
from core.tools.errors import (
ToolEngineInvokeError,
ToolInvokeError,
@@ -40,6 +47,16 @@ from models.model import Message, MessageFile
logger = logging.getLogger(__name__)
@dataclass(frozen=True)
class ToolAgentInvokeResult:
"""Agent-facing tool result with UI kept outside the model observation."""
observation: str
message_files: list[str]
ui_messages: list[ToolUIMessage]
meta: ToolInvokeMeta
class ToolEngine:
"""
Tool runtime engine take care of the tool executions.
@@ -59,9 +76,13 @@ class ToolEngine:
conversation_id: str | None = None,
app_id: str | None = None,
message_id: str | None = None,
) -> tuple[str, list[str], ToolInvokeMeta]:
) -> ToolAgentInvokeResult:
"""
Agent invokes the tool with the given arguments.
Invoke a tool for an agent.
UI messages are validated and returned on a dedicated channel. They are
intentionally excluded from both the LLM observation and tracing
callback output.
"""
# check if arguments is a string
if isinstance(tool_parameters, str):
@@ -103,7 +124,7 @@ class ToolEngine:
conversation_id=message.conversation_id,
)
message_list = list(messages)
message_list, ui_messages = ToolEngine.collect_agent_messages(messages)
# extract binary data from tool invoke message
binary_files = ToolEngine._extract_tool_response_binary_and_text(message_list)
@@ -126,7 +147,12 @@ class ToolEngine:
)
# transform tool invoke message to get LLM friendly message
return plain_text, message_files, meta
return ToolAgentInvokeResult(
observation=plain_text,
message_files=message_files,
ui_messages=ui_messages,
meta=meta,
)
except ToolProviderCredentialValidationError as e:
logger.error(e, exc_info=True)
error_response = "Please check your tool provider credentials"
@@ -148,13 +174,23 @@ class ToolEngine:
error_response = f"tool invoke error: {meta.error}"
agent_tool_callback.on_tool_error(e)
logger.error(e, exc_info=True)
return error_response, [], meta
return ToolAgentInvokeResult(
observation=error_response,
message_files=[],
ui_messages=[],
meta=meta,
)
except Exception as e:
error_response = f"unknown error: {e}"
agent_tool_callback.on_tool_error(e)
logger.error(e, exc_info=True)
return error_response, [], ToolInvokeMeta.error_instance(error_response)
return ToolAgentInvokeResult(
observation=error_response,
message_files=[],
ui_messages=[],
meta=ToolInvokeMeta.error_instance(error_response),
)
@staticmethod
def generic_invoke(
@@ -197,7 +233,7 @@ class ToolEngine:
tool_outputs=response,
)
return response
return ToolEngine.normalize_ui_messages(response)
except Exception as e:
workflow_tool_callback.on_tool_error(e)
raise e
@@ -266,7 +302,10 @@ class ToolEngine:
ensure_ascii=False,
)
)
elif response.type == ToolInvokeMessage.MessageType.VARIABLE:
elif response.type in {
ToolInvokeMessage.MessageType.VARIABLE,
ToolInvokeMessage.MessageType.UI,
}:
continue
else:
parts.append(str(response.message))
@@ -278,6 +317,124 @@ class ToolEngine:
return "".join(parts)
@staticmethod
def normalize_ui_messages(messages: Iterable[ToolInvokeMessage]) -> Generator[ToolInvokeMessage, None, None]:
"""Convert reserved variable/JSON compatibility envelopes into native UI."""
for message in messages:
if message.type == ToolInvokeMessage.MessageType.VARIABLE:
variable_message = cast(ToolInvokeMessage.VariableMessage, message.message)
if variable_message.variable_name != DIFY_UI_JSON_ENVELOPE_KEY:
yield message
continue
yield ToolInvokeMessage(
type=ToolInvokeMessage.MessageType.UI,
message=ToolUIMessage.model_validate(variable_message.variable_value),
meta=message.meta,
)
continue
if message.type != ToolInvokeMessage.MessageType.JSON:
yield message
continue
json_message = cast(ToolInvokeMessage.JsonMessage, message.message)
ui_message = extract_ui_message_from_json(json_message.json_object)
if ui_message is None:
yield message
continue
yield ToolInvokeMessage(type=ToolInvokeMessage.MessageType.UI, message=ui_message, meta=message.meta)
@staticmethod
def collect_agent_messages(
messages: Iterable[ToolInvokeMessage],
) -> tuple[list[ToolInvokeMessage], list[ToolUIMessage]]:
"""Collect a bounded UI batch while preserving all non-UI observations.
A malformed or over-budget UI message invalidates the complete UI
batch. Remaining UI is skipped without parsing, but the input iterable
is still consumed so later text and file messages are retained.
"""
normalized_messages: list[ToolInvokeMessage] = []
ui_messages: list[ToolUIMessage] = []
ui_batch_rejected = False
for message in messages:
is_ui_transport = ToolEngine._is_ui_transport_message(message)
if ui_batch_rejected and is_ui_transport:
continue
try:
normalized = ToolEngine.normalize_ui_messages([message])
except (TypeError, ValueError):
if not is_ui_transport:
raise
# Reserved UI envelopes must never fall back to JSON/variable
# observations, even when malformed.
ui_batch_rejected = True
ui_messages.clear()
normalized_messages = [
normalized_message
for normalized_message in normalized_messages
if normalized_message.type != ToolInvokeMessage.MessageType.UI
]
logger.warning("Ignored invalid reserved tool UI message", exc_info=True)
continue
try:
for normalized_message in normalized:
if normalized_message.type != ToolInvokeMessage.MessageType.UI:
normalized_messages.append(normalized_message)
continue
if ui_batch_rejected:
continue
ui_message = cast(ToolUIMessage, normalized_message.message)
candidate = [*ui_messages, ui_message]
try:
validate_tool_ui_message_batch(candidate)
except ValueError:
ui_batch_rejected = True
ui_messages.clear()
normalized_messages = [
collected_message
for collected_message in normalized_messages
if collected_message.type != ToolInvokeMessage.MessageType.UI
]
logger.warning(
"Ignored tool UI batch that exceeds agent invocation limits",
exc_info=True,
)
continue
ui_messages = candidate
normalized_messages.append(normalized_message)
except (TypeError, ValueError):
if not is_ui_transport:
raise
ui_batch_rejected = True
ui_messages.clear()
normalized_messages = [
normalized_message
for normalized_message in normalized_messages
if normalized_message.type != ToolInvokeMessage.MessageType.UI
]
logger.warning("Ignored invalid reserved tool UI message", exc_info=True)
return normalized_messages, ui_messages
@staticmethod
def _is_ui_transport_message(message: ToolInvokeMessage) -> bool:
if message.type == ToolInvokeMessage.MessageType.UI:
return True
if message.type == ToolInvokeMessage.MessageType.VARIABLE:
variable_message = cast(ToolInvokeMessage.VariableMessage, message.message)
return variable_message.variable_name == DIFY_UI_JSON_ENVELOPE_KEY
if message.type == ToolInvokeMessage.MessageType.JSON:
json_message = cast(ToolInvokeMessage.JsonMessage, message.message)
value = json_message.json_object
return isinstance(value, dict) and set(value) == {DIFY_UI_JSON_ENVELOPE_KEY}
return False
@staticmethod
def _extract_tool_response_binary_and_text(
tool_response: list[ToolInvokeMessage],
+7
View File
@@ -90,6 +90,7 @@ from .system_variables import SystemVariableKey, get_system_text
if TYPE_CHECKING:
from core.tools.__base.tool import Tool
from core.tools.entities.tool_entities import ToolInvokeMessage as CoreToolInvokeMessage
from core.tools.entities.ui_entities import ToolUIMessage
from graphon.nodes.llm.file_saver import LLMFileSaver
from graphon.nodes.tool.entities import ToolNodeData
@@ -666,6 +667,11 @@ class DifyToolNodeRuntime(ToolNodeRuntimeProtocol):
) -> Generator[ToolRuntimeMessage, None, None]:
try:
for message in messages:
# Tool Gen-UI is currently a chat presentation channel. Graphon
# does not define an equivalent runtime message, so workflow
# execution safely ignores it instead of coercing it to JSON.
if message.type.value == "ui":
continue
yield self._convert_message(message)
except Exception as exc:
raise self._map_invocation_exception(exc, provider_name=provider_name) from exc
@@ -686,6 +692,7 @@ class DifyToolNodeRuntime(ToolNodeRuntimeProtocol):
| CoreToolInvokeMessage.FileMessage
| CoreToolInvokeMessage.VariableMessage
| CoreToolInvokeMessage.RetrieverResourceMessage
| ToolUIMessage
| None,
) -> (
ToolRuntimeMessage.TextMessage
@@ -2,7 +2,7 @@ from __future__ import annotations
from collections.abc import Mapping
from dataclasses import dataclass
from typing import Any, Literal, Protocol, cast
from typing import Any, Final, Literal, Protocol
from dify_agent.layers.dify_core_tools import DifyCoreToolConfig, DifyCoreToolProviderType, DifyCoreToolsLayerConfig
from dify_agent.layers.dify_plugin import (
@@ -29,6 +29,13 @@ from models.provider_ids import ToolProviderID
from models.tools import WorkflowToolProvider
from services.tools.mcp_tools_manage_service import MCPToolManageService
_CORE_TOOL_PROVIDER_TYPES: Final[dict[ToolProviderType, DifyCoreToolProviderType]] = {
ToolProviderType.BUILT_IN: "builtin",
ToolProviderType.API: "api",
ToolProviderType.WORKFLOW: "workflow",
ToolProviderType.MCP: "mcp",
}
class WorkflowAgentDifyToolsBuildError(ValueError):
"""Raised when Agent Soul tools cannot be prepared for Agent backend."""
@@ -235,7 +242,7 @@ class WorkflowAgentDifyToolsBuilder:
if tool_config.tool_name is not None:
expanded.append(tool_config)
continue
provider_type = ToolProviderType.value_of(tool_config.provider_type)
provider_type = tool_config.provider_type
provider_id = self._provider_id(tool_config)
try:
tool_names = self._provider_declared_tool_names(
@@ -279,7 +286,7 @@ class WorkflowAgentDifyToolsBuilder:
tenant_id: str,
tool_config: AgentSoulDifyToolConfig,
) -> AgentSoulDifyToolConfig:
if tool_config.provider_type != ToolProviderType.MCP.value:
if tool_config.provider_type is not ToolProviderType.MCP:
return tool_config
provider_id = self._mcp_provider_id_resolver(tenant_id=tenant_id, provider_id=self._provider_id(tool_config))
return tool_config.model_copy(update={"provider_id": provider_id, "plugin_id": None, "provider": None})
@@ -326,7 +333,7 @@ class WorkflowAgentDifyToolsBuilder:
def _to_agent_tool_entity(tool_config: AgentSoulDifyToolConfig) -> AgentToolEntity:
assert tool_config.tool_name is not None
return AgentToolEntity(
provider_type=ToolProviderType.value_of(tool_config.provider_type),
provider_type=tool_config.provider_type,
provider_id=WorkflowAgentDifyToolsBuilder._provider_id(tool_config),
tool_name=tool_config.tool_name,
tool_parameters=dict(tool_config.runtime_parameters),
@@ -343,24 +350,16 @@ class WorkflowAgentDifyToolsBuilder:
@staticmethod
def _provider_key(tool_config: AgentSoulDifyToolConfig) -> tuple[ToolProviderType, str]:
return (
ToolProviderType.value_of(tool_config.provider_type),
WorkflowAgentDifyToolsBuilder._provider_id(tool_config),
)
return (tool_config.provider_type, WorkflowAgentDifyToolsBuilder._provider_id(tool_config))
@staticmethod
def _tool_layer_destination(tool_config: AgentSoulDifyToolConfig) -> Literal["plugin", "core"]:
provider_type = ToolProviderType.value_of(tool_config.provider_type)
provider_type = tool_config.provider_type
if provider_type is ToolProviderType.PLUGIN or (
provider_type is ToolProviderType.BUILT_IN and _is_plugin_provider_id(tool_config.provider_id)
):
return "plugin"
if provider_type in {
ToolProviderType.BUILT_IN,
ToolProviderType.API,
ToolProviderType.WORKFLOW,
ToolProviderType.MCP,
}:
if provider_type in _CORE_TOOL_PROVIDER_TYPES:
return "core"
if provider_type is ToolProviderType.DATASET_RETRIEVAL:
raise WorkflowAgentDifyToolsBuildError(
@@ -417,7 +416,7 @@ class WorkflowAgentDifyToolsBuilder:
) -> DifyCoreToolConfig:
parameters = self._prepared_parameters(tool_runtime)
return DifyCoreToolConfig(
provider_type=cast(DifyCoreToolProviderType, tool_config.provider_type),
provider_type=_CORE_TOOL_PROVIDER_TYPES[tool_config.provider_type],
provider_id=self._provider_id(tool_config),
tool_name=tool_config.tool_name or exposed_name,
credential_id=tool_config.credential_ref.id if tool_config.credential_ref else None,
+134 -4
View File
@@ -12,6 +12,7 @@ import json
import subprocess
import sys
import tempfile
from copy import deepcopy
from pathlib import Path
from typing import Any, Literal, TypedDict
@@ -24,6 +25,16 @@ LOCK_PATH = API_ROOT / "knowledge-fs-contract.lock.json"
DEFAULT_REPOSITORY = WORKSPACE_ROOT.parent / "knowledge-fs"
OPENAPI_METHODS = ("delete", "get", "head", "options", "patch", "post", "put", "trace")
PROXY_METHODS = frozenset({"delete", "get", "patch", "post", "put"})
CONSOLE_PROXY_ERROR_SCHEMA_NAME = "ConsoleProxyError"
CONSOLE_PROXY_ERROR_SCHEMA: dict[str, Any] = {
"type": "object",
"required": ["code", "message", "status"],
"properties": {
"code": {"type": "string"},
"message": {"type": "string"},
"status": {"type": "integer"},
},
}
class ContractDeclaration(TypedDict):
@@ -38,6 +49,7 @@ class ContractDeclaration(TypedDict):
request_headers: tuple[str, ...]
response_headers: tuple[str, ...]
response_media_types: tuple[str, ...]
error_status_map: tuple[tuple[int, int], ...]
type DeclarationField = Literal[
@@ -70,6 +82,7 @@ def main() -> None:
mode.add_argument("--check", action="store_true")
mode.add_argument("--update-lock", action="store_true")
parser.add_argument("--repository", type=Path, default=DEFAULT_REPOSITORY)
parser.add_argument("--output-openapi", type=Path)
args = parser.parse_args()
repository = args.repository.resolve()
@@ -101,7 +114,15 @@ def main() -> None:
)
document: dict[str, Any] = json.loads(openapi_content)
validate_declarations(document, console_contract_declarations())
declarations = console_contract_declarations()
validate_declarations(document, declarations)
if args.output_openapi:
filtered_document = filter_openapi_document(document, declarations)
filtered_document["x-dify-source-openapi-sha256"] = openapi_sha256
filtered_document["x-dify-console-declarations-sha256"] = contract_declarations_sha256(declarations)
args.output_openapi.parent.mkdir(parents=True, exist_ok=True)
args.output_openapi.write_text(json.dumps(filtered_document, indent=2) + "\n")
if args.update_lock:
LOCK_PATH.write_text(
@@ -147,8 +168,7 @@ def validate_declarations(document: dict[str, Any], declarations: tuple[Contract
raise ValueError(f"KnowledgeFS OpenAPI path must be absolute: {path}")
if method not in PROXY_METHODS:
raise ValueError(f"KnowledgeFS proxy does not support {method.upper()} {path}")
expected: ContractDeclaration = {
"operation_id": operation_id,
expected: dict[DeclarationField, object] = {
"method": method.upper(),
"path": path[1:],
"required_scope": required_scope(operation),
@@ -166,11 +186,114 @@ def validate_declarations(document: dict[str, Any], declarations: tuple[Contract
f"KnowledgeFS operation {operation_id} field {field} drifted: "
f"expected {expected_value!r}, received {received_value!r}"
)
validate_error_status_map(operation_id, declaration["error_status_map"])
def filter_openapi_document(
document: dict[str, Any],
declarations: tuple[ContractDeclaration, ...],
) -> dict[str, Any]:
"""Return a code-generation document containing only Console-allowlisted operations."""
filtered_document: dict[str, Any] = {
key: value for key, value in document.items() if key not in {"components", "paths"}
}
source_paths = document.get("paths", {})
filtered_paths: dict[str, Any] = {}
for declaration in declarations:
path = f"/{declaration['path']}"
method = declaration["method"].lower()
source_path_item = source_paths[path]
path_metadata = {key: value for key, value in source_path_item.items() if key not in OPENAPI_METHODS}
filtered_path_item = filtered_paths.setdefault(path, path_metadata)
filtered_operation = deepcopy(source_path_item[method])
_rewrite_proxy_error_responses(filtered_operation, declaration["error_status_map"])
filtered_path_item[method] = filtered_operation
filtered_document["paths"] = filtered_paths
source_components = document.get("components", {})
filtered_components = {key: value for key, value in source_components.items() if key != "schemas"}
source_schemas = source_components.get("schemas", {})
available_schemas = {**source_schemas, CONSOLE_PROXY_ERROR_SCHEMA_NAME: CONSOLE_PROXY_ERROR_SCHEMA}
schema_names = _referenced_schema_names(filtered_paths, available_schemas)
filtered_components["schemas"] = {
name: schema for name, schema in available_schemas.items() if name in schema_names
}
filtered_document["components"] = filtered_components
return filtered_document
def validate_error_status_map(operation_id: str, error_status_map: tuple[tuple[int, int], ...]) -> None:
"""Validate the status normalization advertised by one Console operation."""
upstream_statuses: set[int] = set()
for upstream_status, console_status in error_status_map:
if upstream_status in upstream_statuses:
raise ValueError(f"KnowledgeFS operation {operation_id} has duplicate error status: {upstream_status}")
if not 400 <= upstream_status <= 599 or not 400 <= console_status <= 599:
raise ValueError(f"KnowledgeFS operation {operation_id} has invalid error status mapping")
upstream_statuses.add(upstream_status)
def _rewrite_proxy_error_responses(
operation: dict[str, Any],
error_status_map: tuple[tuple[int, int], ...],
) -> None:
responses = operation.setdefault("responses", {})
proxy_error_response = {
"description": "Error normalized by the Dify Console KnowledgeFS proxy.",
"content": {
"application/json": {"schema": {"$ref": f"#/components/schemas/{CONSOLE_PROXY_ERROR_SCHEMA_NAME}"}}
},
}
for upstream_status, console_status in error_status_map:
existing_target = responses.get(str(console_status)) if upstream_status != console_status else None
responses.pop(str(upstream_status), None)
normalized_response: dict[str, Any] = deepcopy(proxy_error_response)
existing_schema = (
existing_target.get("content", {}).get("application/json", {}).get("schema")
if isinstance(existing_target, dict)
else None
)
if existing_schema is not None:
normalized_response["content"]["application/json"]["schema"] = {
"oneOf": [
deepcopy(existing_schema),
{"$ref": f"#/components/schemas/{CONSOLE_PROXY_ERROR_SCHEMA_NAME}"},
]
}
responses[str(console_status)] = normalized_response
def _referenced_schema_names(value: Any, schemas: dict[str, Any]) -> set[str]:
reference_prefix = "#/components/schemas/"
selected: set[str] = set()
pending: list[Any] = [value]
while pending:
current = pending.pop()
if isinstance(current, list):
pending.extend(current)
continue
if not isinstance(current, dict):
continue
reference = current.get("$ref")
if isinstance(reference, str) and reference.startswith(reference_prefix):
name = reference.removeprefix(reference_prefix)
if name not in selected:
if name not in schemas:
raise ValueError(f"KnowledgeFS OpenAPI references missing schema: {name}")
selected.add(name)
pending.append(schemas[name])
pending.extend(current.values())
return selected
def console_contract_declarations() -> tuple[ContractDeclaration, ...]:
"""Return transport declarations from the runtime Console operation registry."""
from services.knowledge_fs_proxy import KNOWLEDGE_FS_CONSOLE_OPERATIONS
from services.knowledge_fs_operations import KNOWLEDGE_FS_CONSOLE_OPERATIONS
return tuple(
{
@@ -183,11 +306,18 @@ def console_contract_declarations() -> tuple[ContractDeclaration, ...]:
"request_headers": operation.request_headers,
"response_headers": operation.response_headers,
"response_media_types": operation.response_media_types,
"error_status_map": operation.error_status_map,
}
for operation in KNOWLEDGE_FS_CONSOLE_OPERATIONS
)
def contract_declarations_sha256(declarations: tuple[ContractDeclaration, ...]) -> str:
"""Return a stable digest for the runtime Console operation declarations."""
content = json.dumps(declarations, separators=(",", ":"), sort_keys=True).encode()
return sha256(content)
def response_kind(operation: dict[str, Any]) -> str:
media_types = response_media_types(operation)
if "text/event-stream" in media_types:
+1
View File
@@ -157,6 +157,7 @@ def init_app(app: DifyApp) -> Celery:
"tasks.regenerate_summary_index_task", # summary index regeneration
"tasks.initialize_created_app_rbac_access_task", # app access initialization
"tasks.install_default_plugins_task", # tenant default plugin installation
"tasks.refresh_billing_vector_space_task", # billing vector-space cache refresh
"tasks.app_generate.resume_agent_app_task", # ENG-635: Agent v2 chat ask_human resume
"tasks.workflow_run_archive_download_tasks", # workflow-run archive download preparation
]
+19 -4
View File
@@ -1,5 +1,6 @@
import json
from typing import cast, override
import logging
from typing import assert_never, cast, override
import flask_login
from flask import Request, Response, request
@@ -11,6 +12,7 @@ from werkzeug.exceptions import NotFound, Unauthorized
from configs import dify_config
from constants import HEADER_NAME_APP_CODE
from core.db.session_factory import session_factory
from core.logging.context import set_identity_context
from dify_app import DifyApp
from libs.passport import PassportService
from libs.token import extract_access_token, extract_console_cookie_token, extract_webapp_passport
@@ -19,6 +21,8 @@ from models.enums import EndUserType
from models.model import AppMCPServer, EndUser
from services.account_service import AccountService
logger = logging.getLogger(__name__)
type LoginUser = Account | EndUser
@@ -156,13 +160,24 @@ def _load_user_from_request(request_from_flask_login: Request, session: Session)
@user_logged_in.connect
@user_loaded_from_request.connect
def on_user_logged_in(_sender: object, user: LoginUser) -> None:
"""Called when a user logged in.
"""Snapshot authenticated identity into the side-effect-free logging context.
Note: AccountService.load_logged_in_account will populate user.current_tenant_id
through the load_user method, which calls account.set_tenant_id_with_session().
"""
# tenant_id context variable removed - using current_user.current_tenant_id directly
pass
set_identity_context()
try:
match user:
case Account():
set_identity_context(tenant_id=user.current_tenant_id, user_id=user.id, user_type="account")
case EndUser():
set_identity_context(tenant_id=user.tenant_id, user_id=user.id, user_type=user.type or "end_user")
case _ as unreachable:
assert_never(unreachable)
except Exception:
# Logging enrichment must never make authentication fail.
logger.exception("Failed to set logging identity context")
return
@login_manager.unauthorized_handler
+13
View File
@@ -119,6 +119,19 @@ class Storage:
def delete(self, filename: str):
return self.storage_runner.delete(filename)
def generate_presigned_url(
self,
filename: str,
*,
expires_in: int,
content_type: str | None = None,
) -> str:
return self.storage_runner.generate_presigned_url(
filename,
expires_in=expires_in,
content_type=content_type,
)
def scan(self, path: str, files: bool = True, directories: bool = False) -> list[str]:
return self.storage_runner.scan(path, files=files, directories=directories)
+8 -3
View File
@@ -69,12 +69,17 @@ def on_user_loaded(_sender, user: Union["Account", "EndUser"]):
if user:
try:
current_span = get_current_span()
if not current_span.is_recording():
return
tenant_id = extract_tenant_id(user)
if not tenant_id:
return
if current_span:
current_span.set_attribute(DifySpanAttributes.TENANT_ID, tenant_id)
current_span.set_attribute(GenAIAttributes.USER_ID, user.id)
current_span.set_attributes(
{
DifySpanAttributes.TENANT_ID: tenant_id,
GenAIAttributes.USER_ID: user.id,
}
)
except Exception:
logger.exception("Error setting tenant and user attributes")
pass
+18
View File
@@ -92,3 +92,21 @@ class AwsS3Storage(BaseStorage):
@override
def delete(self, filename: str):
self.client.delete_object(Bucket=self.bucket_name, Key=filename)
@override
def generate_presigned_url(
self,
filename: str,
*,
expires_in: int,
content_type: str | None = None,
) -> str:
params = {"Bucket": self.bucket_name, "Key": filename}
if content_type:
params["ResponseContentType"] = content_type
return self.client.generate_presigned_url(
"get_object",
Params=params,
ExpiresIn=expires_in,
)
+10
View File
@@ -31,6 +31,16 @@ class BaseStorage(ABC):
def delete(self, filename: str):
raise NotImplementedError
def generate_presigned_url(
self,
filename: str,
*,
expires_in: int,
content_type: str | None = None,
) -> str:
"""Generate a temporary direct-download URL when the backend supports it."""
raise NotImplementedError("This storage backend doesn't support presigned URLs")
def scan(self, path, files=True, directories=False) -> list[str]:
"""
Scan files and directories in the given path.
+8
View File
@@ -7,6 +7,7 @@ from uuid import uuid4
from pydantic import Field, computed_field, field_validator
from core.entities.execution_extra_content import ExecutionExtraContentDomainModel
from core.tools.entities.ui_entities import MessageUIPart, parse_history_ui_parts
from fields.base import ResponseModel
from fields.conversation_fields import AgentThought, JSONValue, MessageFile
from graphon.file import File
@@ -64,6 +65,7 @@ class MessageListItem(ResponseModel):
status: str
error: str | None = None
extra_contents: list[ExecutionExtraContentDomainModel]
ui_parts: list[MessageUIPart] = Field(default_factory=list, validation_alias="message_metadata_dict")
@computed_field
def total_tokens(self) -> int:
@@ -79,6 +81,12 @@ class MessageListItem(ResponseModel):
def _normalize_created_at(cls, value: datetime | int | None) -> int | None:
return to_timestamp(value)
@field_validator("ui_parts", mode="before")
@classmethod
def _normalize_ui_parts(cls, value: object) -> list[MessageUIPart]:
raw_parts = value.get("ui_parts", []) if isinstance(value, dict) else value
return parse_history_ui_parts(raw_parts)
class WebMessageListItem(MessageListItem):
metadata: JSONValueType | None = Field(
+2 -2
View File
@@ -1,5 +1,5 @@
{
"commit": "4310e2d582d25e7de58183f27720afab01e123cf",
"openapiSha256": "5827ca930ce38462bfd1b2bef387efbf37eb7ffcaedde4558af2fbaeccbfbc4b",
"commit": "a0f50470612cc0b3656f89e4f2435aaf412e6e3b",
"openapiSha256": "f18910e9c45a64f0855e0643a7a626fb2889021b4f943458de86c6bd2469facb",
"repository": "https://github.com/langgenius/knowledge-fs"
}
+17
View File
@@ -9,6 +9,8 @@ from werkzeug.http import HTTP_STATUS_CODES
from configs import dify_config
from core.errors.error import AppInvokeQuotaExceededError
from core.plugin.impl.exc import PluginRuntimeError
from extensions.ext_logging import get_request_id
from libs.flask_restx_compat import install_swagger_compatibility
from libs.token import build_force_logout_cookie_headers
@@ -100,6 +102,20 @@ def register_external_error_handlers(api: Api, body_formatter: ErrorBodyFormatte
data = {"code": "too_many_requests", "message": str(e), "status": status_code}
return _finalize(e, data, status_code), status_code
def handle_plugin_runtime_error(e: PluginRuntimeError):
got_request_exception.send(current_app, exception=e)
status_code = 502
details = {"request_id": get_request_id()}
if e.lambda_request_id:
details["lambda_request_id"] = e.lambda_request_id
data = {
"code": "plugin_runtime_error",
"message": e.description,
"details": details,
"status": status_code,
}
return _finalize(e, data, status_code), status_code
def handle_general_exception(e: Exception):
got_request_exception.send(current_app, exception=e)
@@ -121,6 +137,7 @@ def register_external_error_handlers(api: Api, body_formatter: ErrorBodyFormatte
api.errorhandler(HTTPException)(handle_http_exception)
api.errorhandler(ValueError)(handle_value_error)
api.errorhandler(AppInvokeQuotaExceededError)(handle_quota_exceeded)
api.errorhandler(PluginRuntimeError)(handle_plugin_runtime_error)
api.errorhandler(Exception)(handle_general_exception)
+5 -2
View File
@@ -221,8 +221,11 @@ def current_timestamp() -> int:
def email(email):
# Define a regex pattern for email addresses
pattern = r"^[\w\.!#$%&'*+\-/=?^_`{|}~]+@([\w-]+\.)+[\w-]{2,}$"
# Check if the email matches the pattern
if re.match(pattern, email) is not None:
# Use re.fullmatch instead of re.match to reject trailing newlines.
# In Python, '$' matches at end-of-string OR just before a trailing newline,
# so re.match accepts "user@example.com\n". re.fullmatch requires the entire
# string to match, closing the mail header-injection vector. (#39234)
if re.fullmatch(pattern, email) is not None:
return email
error = f"{email} is not a valid email."
+2 -2
View File
@@ -23,9 +23,9 @@ class PaginatedResult[T]:
@property
def pages(self) -> int:
if self.per_page == 0:
if self.total == 0 or self.per_page == 0:
return 0
return max(1, math.ceil(self.total / self.per_page))
return math.ceil(self.total / self.per_page)
@property
def has_next(self) -> bool:
@@ -0,0 +1,77 @@
"""scope agent debug conversations by draft type
Revision ID: d2825e7b9c10
Revises: b8c9d0e1f2a3
Create Date: 2026-07-22 15:00:00.000000
"""
import sqlalchemy as sa
from alembic import op
import models
# revision identifiers, used by Alembic.
revision = "d2825e7b9c10"
down_revision = "b8c9d0e1f2a3"
branch_labels = None
depends_on = None
def upgrade():
# Existing pointers have always represented Build chat because the Agent
# detail API exposes them as ``debug_conversation_id`` for that surface.
op.add_column(
"agent_debug_conversations",
sa.Column(
"draft_type",
sa.String(length=32),
nullable=False,
server_default=sa.text("'debug_build'"),
),
)
op.drop_constraint(
"agent_debug_conversation_agent_account_unique",
"agent_debug_conversations",
type_="unique",
)
op.create_unique_constraint(
"agent_debug_conversation_agent_account_draft_type_unique",
"agent_debug_conversations",
["tenant_id", "agent_id", "account_id", "draft_type"],
)
def downgrade():
debug_conversations = sa.table(
"agent_debug_conversations",
sa.column("tenant_id", models.types.StringUUID()),
sa.column("agent_id", models.types.StringUUID()),
sa.column("account_id", models.types.StringUUID()),
sa.column("draft_type", sa.String(length=32)),
)
build_conversations = debug_conversations.alias("build_conversations")
op.get_bind().execute(
sa.delete(debug_conversations).where(
debug_conversations.c.draft_type == "draft",
sa.exists(
sa.select(sa.literal(1)).where(
build_conversations.c.tenant_id == debug_conversations.c.tenant_id,
build_conversations.c.agent_id == debug_conversations.c.agent_id,
build_conversations.c.account_id == debug_conversations.c.account_id,
build_conversations.c.draft_type == "debug_build",
)
),
)
)
op.drop_constraint(
"agent_debug_conversation_agent_account_draft_type_unique",
"agent_debug_conversations",
type_="unique",
)
op.create_unique_constraint(
"agent_debug_conversation_agent_account_unique",
"agent_debug_conversations",
["tenant_id", "agent_id", "account_id"],
)
op.drop_column("agent_debug_conversations", "draft_type")
+12 -3
View File
@@ -222,11 +222,13 @@ class Agent(DefaultFieldsMixin, Base):
class AgentDebugConversation(DefaultFieldsMixin, Base):
"""Per-account console debug conversation for an Agent App.
"""Per-account, per-draft console debug conversation for an Agent App.
Agent App preview state must be isolated by editor account. The Agent row is
shared by everyone in the workspace, so this table owns the user-specific
conversation pointer used by console debug chat.
conversation pointers used by console debug chat. ``draft`` is the Preview
conversation and ``debug_build`` is the Build conversation; they must never
share persisted messages or runtime sessions.
"""
__tablename__ = "agent_debug_conversations"
@@ -236,7 +238,8 @@ class AgentDebugConversation(DefaultFieldsMixin, Base):
"tenant_id",
"agent_id",
"account_id",
name="agent_debug_conversation_agent_account_unique",
"draft_type",
name="agent_debug_conversation_agent_account_draft_type_unique",
),
Index("agent_debug_conversation_conversation_idx", "conversation_id"),
Index("agent_debug_conversation_account_idx", "tenant_id", "account_id"),
@@ -246,6 +249,12 @@ class AgentDebugConversation(DefaultFieldsMixin, Base):
agent_id: Mapped[str] = mapped_column(StringUUID, nullable=False)
app_id: Mapped[str] = mapped_column(StringUUID, nullable=False)
account_id: Mapped[str] = mapped_column(StringUUID, nullable=False)
draft_type: Mapped[AgentConfigDraftType] = mapped_column(
EnumText(AgentConfigDraftType, length=32),
nullable=False,
default=AgentConfigDraftType.DEBUG_BUILD,
server_default=sa.text("'debug_build'"),
)
conversation_id: Mapped[str] = mapped_column(StringUUID, nullable=False)
+22 -15
View File
@@ -7,6 +7,7 @@ from typing import Annotated, Any, Final, Literal, Self
from pydantic import BaseModel, ConfigDict, Field, WithJsonSchema, field_validator, model_validator
from core.rag.entities.metadata_entities import ConditionValue, SupportedComparisonOperator
from core.tools.entities.tool_entities import ToolProviderType
from core.workflow.file_reference import is_canonical_file_reference
from graphon.file import FileTransferMethod, FileType
@@ -43,18 +44,28 @@ _DECLARED_OUTPUT_CHILDREN_JSON_SCHEMA = {
},
"description": {"anyOf": [{"type": "string"}, {"type": "null"}]},
"required": {"type": "boolean"},
"file": {"type": "object", "additionalProperties": True},
"file": {
"anyOf": [
{"type": "object", "additionalProperties": True},
{"type": "null"},
]
},
"array_item": {
"type": "object",
"additionalProperties": True,
"properties": {
"type": {
"type": "string",
"enum": [item.value for item in DeclaredOutputType],
"anyOf": [
{
"type": "object",
"additionalProperties": True,
"properties": {
"type": {
"type": "string",
"enum": [item.value for item in DeclaredOutputType],
},
"description": {"anyOf": [{"type": "string"}, {"type": "null"}]},
"children": {"type": "array", "items": {"type": "object", "additionalProperties": True}},
},
},
"description": {"anyOf": [{"type": "string"}, {"type": "null"}]},
"children": {"type": "array", "items": {"type": "object", "additionalProperties": True}},
},
{"type": "null"},
]
},
"children": {"type": "array", "items": {"type": "object", "additionalProperties": True}},
},
@@ -653,11 +664,7 @@ class AgentSoulDifyToolConfig(BaseModel):
model_config = ConfigDict(extra="ignore")
enabled: bool = True
# ``plugin`` remains the default for legacy Agent Soul payloads. The runtime
# now also accepts ``builtin`` / ``api`` / ``workflow`` / ``mcp`` here and
# routes them through ``dify.core.tools``; keeping the default narrow still
# makes a missing field resolve against the plugin provider table.
provider_type: str = "plugin"
provider_type: ToolProviderType
provider_id: str | None = Field(default=None, max_length=255)
plugin_id: str | None = Field(default=None, max_length=255)
provider: str | None = Field(default=None, max_length=255)
+32 -14
View File
@@ -56,6 +56,7 @@ from .provider_ids import GenericProviderID
from .types import EnumText, LongText, StringUUID
if TYPE_CHECKING:
from .agent import Agent
from .workflow import Workflow
@@ -501,25 +502,42 @@ class App(Base):
Resolved via ``Agent.app_id`` so the console can open the Composer in
roster-detail mode from the app id. ``None`` for non-agent apps.
"""
agent = self.agent_app_binding_with_session(session=session)
return agent.id if agent else None
def agent_app_binding_with_session(self, *, session: Session, include_archived: bool = False) -> Agent | None:
"""For an Agent App (mode=agent), the Agent bound to it.
A roster Agent is bound through ``Agent.app_id``; a workflow-only Agent
is bound to its hidden runtime backing App through
``Agent.backing_app_id``. Callers branch on ``Agent.scope`` to tell the
public roster Agent App apart from the hidden backing App. Archived
Agents are excluded unless ``include_archived`` is set (authorization
gates must keep covering an Agent App after its Agent is archived).
``None`` for non-agent apps and unbound agent apps.
"""
if self.mode != AppMode.AGENT:
return None
from .agent import APP_BACKED_AGENT_SOURCES, Agent, AgentScope, AgentStatus
agent = session.scalar(
select(Agent).where(
Agent.tenant_id == self.tenant_id,
sa.or_(
sa.and_(
Agent.app_id == self.id,
Agent.scope == AgentScope.ROSTER,
Agent.source.in_(APP_BACKED_AGENT_SOURCES),
),
Agent.backing_app_id == self.id,
conditions = [
Agent.tenant_id == self.tenant_id,
sa.or_(
sa.and_(
Agent.app_id == self.id,
Agent.scope == AgentScope.ROSTER,
Agent.source.in_(APP_BACKED_AGENT_SOURCES),
),
Agent.status == AgentStatus.ACTIVE,
)
)
return agent.id if agent else None
sa.and_(
Agent.backing_app_id == self.id,
Agent.scope == AgentScope.WORKFLOW_ONLY,
),
),
]
if not include_archived:
conditions.append(Agent.status == AgentStatus.ACTIVE)
return session.scalar(select(Agent).where(*conditions).limit(1))
@property
def api_base_url(self) -> str:
+67 -11
View File
@@ -260,7 +260,12 @@ Get account avatar url
| 200 | Success | **application/json**: [AccountResponse](#accountresponse)<br> |
### [POST] /activate
**Accept an invitation without letting an existing session act for another account**
Activate account with invitation token
Token-only activation remains available for legacy clients. When the request already
carries a console session, that session must belong to the account encoded in the
invitation before the token is consumed or tenant membership is changed.
#### Request Body
@@ -531,6 +536,7 @@ Run a build-draft Agent App turn that asks the agent to push config updates
| Code | Description | Schema |
| ---- | ----------- | ------ |
| 200 | Agent build draft | **application/json**: [AgentBuildDraftResponse](#agentbuilddraftresponse)<br> |
| 404 | Agent build draft not found | |
### [PUT] /agent/{agent_id}/build-draft
#### Parameters
@@ -958,6 +964,12 @@ Stop a running Agent App chat message generation
| ---- | ---------- | ----------- | -------- | ------ |
| agent_id | path | | Yes | string (uuid) |
#### Request Body
| Required | Schema |
| -------- | ------ |
| No | **application/json**: [AgentDebugConversationRefreshPayload](#agentdebugconversationrefreshpayload)<br> |
#### Responses
| Code | Description | Schema |
@@ -11332,6 +11344,12 @@ Returns permission flags that control workspace features like member invitations
| 200 | Success | **application/json**: [PluginDecodeResponse](#plugindecoderesponse)<br> |
### [POST] /workspaces/current/plugin/upload/pkg
#### Request Body
| Required | Schema |
| -------- | ------ |
| Yes | **multipart/form-data**: { **"pkg"**: binary }<br> |
#### Responses
| Code | Description | Schema |
@@ -13278,7 +13296,7 @@ Model class for AI model.
| maintainer | string | | No |
| max_active_requests | integer | | No |
| mode | string | | Yes |
| model_config | [ModelConfig](#modelconfig) | | No |
| model_config | [AppModelConfigResponse](#appmodelconfigresponse) | | No |
| name | string | | Yes |
| permission_keys | [ string ] | | No |
| role | string | | No |
@@ -13899,6 +13917,12 @@ Stable Agent Soul reference to one normalized skill archive.
| date | string | | Yes |
| message_count | integer | | Yes |
#### AgentDebugConversationRefreshPayload
| Name | Type | Description | Required |
| ---- | ---- | ----------- | -------- |
| draft_type | [AgentConfigDraftType](#agentconfigdrafttype) | Agent draft surface whose conversation should be refreshed | No |
#### AgentDebugConversationRefreshResponse
| Name | Type | Description | Required |
@@ -14737,7 +14761,7 @@ should send ``plugin_id`` + ``provider`` when available.
| plugin_id | string | | No |
| provider | string | | No |
| provider_id | string | | No |
| provider_type | string, <br>**Default:** plugin | | No |
| provider_type | [ToolProviderType](#toolprovidertype) | | Yes |
| runtime_parameters | object | | No |
| tool_name | string | | No |
@@ -15348,7 +15372,6 @@ This class is used to store the schema information of an api based tool.
| Name | Type | Description | Required |
| ---- | ---- | ----------- | -------- |
| access_mode | string | | No |
| app_model_config | [ModelConfig](#modelconfig) | | No |
| created_at | integer | | No |
| created_by | string | | No |
| description | string | | No |
@@ -15358,7 +15381,8 @@ This class is used to store the schema information of an api based tool.
| icon_background | string | | No |
| id | string | | Yes |
| maintainer | string | | No |
| mode_compatible_with_agent | string | | Yes |
| mode | string | | Yes |
| model_config | [AppModelConfigResponse](#appmodelconfigresponse) | | No |
| name | string | | Yes |
| permission_keys | [ string ] | | No |
| tags | [ [Tag](#tag) ] | | No |
@@ -15420,7 +15444,7 @@ This class is used to store the schema information of an api based tool.
| maintainer | string | | No |
| max_active_requests | integer | | No |
| mode | string | | Yes |
| model_config | [ModelConfig](#modelconfig) | | No |
| model_config | [AppModelConfigResponse](#appmodelconfigresponse) | | No |
| name | string | | Yes |
| permission_keys | [ string ] | | No |
| site | [AppDetailSiteResponse](#appdetailsiteresponse) | | No |
@@ -15519,6 +15543,35 @@ AppMCPServer Status Enum
| ---- | ---- | ----------- | -------- |
| AppMCPServerStatus | string | AppMCPServer Status Enum | |
#### AppModelConfigResponse
| Name | Type | Description | Required |
| ---- | ---- | ----------- | -------- |
| agent_mode | | | No |
| annotation_reply | | | No |
| chat_prompt_config | | | No |
| completion_prompt_config | | | No |
| created_at | integer | | No |
| created_by | string | | No |
| dataset_configs | | | No |
| dataset_query_variable | string | | No |
| external_data_tools | | | No |
| file_upload | | | No |
| model | | | No |
| more_like_this | | | No |
| opening_statement | string | | No |
| pre_prompt | string | | No |
| prompt_type | string | | No |
| retriever_resource | | | No |
| sensitive_word_avoidance | | | No |
| speech_to_text | | | No |
| suggested_questions | | | No |
| suggested_questions_after_answer | | | No |
| text_to_speech | | | No |
| updated_at | integer | | No |
| updated_by | string | | No |
| user_input_form | | | No |
#### AppNamePayload
| Name | Type | Description | Required |
@@ -17147,7 +17200,7 @@ about. Stage 4 §4.2.
| Name | Type | Description | Required |
| ---- | ---- | ----------- | -------- |
| children | [ { **"array_item"**: { **"children"**: [ object ], **"description"**: , **"type"**: string, <br>**Available values:** "array", "boolean", "file", "number", "object", "string" }, **"children"**: [ object ], **"description"**: , **"file"**: object, **"name"**: string, **"required"**: boolean, **"type"**: string, <br>**Available values:** "array", "boolean", "file", "number", "object", "string" } ] | | No |
| children | [ { **"array_item"**: , **"children"**: [ object ], **"description"**: , **"file"**: , **"name"**: string, **"required"**: boolean, **"type"**: string, <br>**Available values:** "array", "boolean", "file", "number", "object", "string" } ] | | No |
| description | string | | No |
| type | [DeclaredOutputType](#declaredoutputtype) | | Yes |
@@ -17176,7 +17229,7 @@ code can call ``output.failure_strategy.on_failure`` without None-guards.
| ---- | ---- | ----------- | -------- |
| array_item | [DeclaredArrayItem](#declaredarrayitem) | | No |
| check | [DeclaredOutputCheckConfig](#declaredoutputcheckconfig) | | No |
| children | [ { **"array_item"**: { **"children"**: [ object ], **"description"**: , **"type"**: string, <br>**Available values:** "array", "boolean", "file", "number", "object", "string" }, **"children"**: [ object ], **"description"**: , **"file"**: object, **"name"**: string, **"required"**: boolean, **"type"**: string, <br>**Available values:** "array", "boolean", "file", "number", "object", "string" } ] | | No |
| children | [ { **"array_item"**: , **"children"**: [ object ], **"description"**: , **"file"**: , **"name"**: string, **"required"**: boolean, **"type"**: string, <br>**Available values:** "array", "boolean", "file", "number", "object", "string" } ] | | No |
| description | string | | No |
| failure_strategy | [DeclaredOutputFailureStrategy](#declaredoutputfailurestrategy) | | No |
| file | [DeclaredOutputFileConfig](#declaredoutputfileconfig) | | No |
@@ -19506,6 +19559,7 @@ Coarse node-level status used by Inspector to pick a banner.
| ---- | ---- | ----------- | -------- |
| avatar | string | | No |
| email | string | | Yes |
| id | string | | Yes |
| interface_language | string | | Yes |
| name | string | | Yes |
| timezone | string | | Yes |
@@ -21954,9 +22008,9 @@ The subscription constructor of the trigger provider
| Name | Type | Description | Required |
| ---- | ---- | ----------- | -------- |
| hash | string | | No |
| result | string | | No |
| updated_at | string | | No |
| hash | string | | Yes |
| result | string | | Yes |
| updated_at | integer | | Yes |
#### SystemConfigurationResponse
@@ -21988,6 +22042,7 @@ Model class for provider system configuration response.
| is_allow_create_workspace | boolean | | Yes |
| is_allow_register | boolean | | Yes |
| is_email_setup | boolean | | Yes |
| knowledge_fs_enabled | boolean | | Yes |
| license | [LicenseModel](#licensemodel) | | Yes |
| max_plugin_package_size | integer, <br>**Default:** 15728640 | | Yes |
| plugin_installation_permission | [PluginInstallationPermissionModel](#plugininstallationpermissionmodel) | | Yes |
@@ -22281,7 +22336,7 @@ Tool label
#### ToolParameter
Overrides type
Tool-specific parameter declaration and invocation-value normalization.
| Name | Type | Description | Required |
| ---- | ---- | ----------- | -------- |
@@ -22294,6 +22349,7 @@ Overrides type
| llm_description | string | | No |
| max | number<br>integer | | No |
| min | number<br>integer | | No |
| multiple | boolean | Whether the parameter is multiple select, only valid for select or dynamic-select type | No |
| name | string | The name of the parameter | Yes |
| options | [ [PluginParameterOption](#pluginparameteroption) ] | | No |
| placeholder | [I18nObject](#i18nobject) | The placeholder presented to the user | No |
+2 -1
View File
@@ -1582,6 +1582,7 @@ Default configuration for form inputs.
| is_allow_create_workspace | boolean | | Yes |
| is_allow_register | boolean | | Yes |
| is_email_setup | boolean | | Yes |
| knowledge_fs_enabled | boolean | | Yes |
| license | [LicenseModel](#licensemodel) | | Yes |
| max_plugin_package_size | integer, <br>**Default:** 15728640 | | Yes |
| plugin_installation_permission | [PluginInstallationPermissionModel](#plugininstallationpermissionmodel) | | Yes |
@@ -1733,7 +1734,7 @@ in form definiton, or a variable while the workflow is running.
| icon | string | | No |
| icon_background | string | | No |
| icon_type | string | | No |
| icon_url | string | | Yes |
| icon_url | string | | No |
| input_placeholder | string | | No |
| privacy_policy | string | | No |
| prompt_public | boolean | | No |
+75
View File
@@ -1164,6 +1164,20 @@ class AgentComposerService:
agent.active_config_is_published = True
agent.updated_by = account_id
binding.current_snapshot_id = version.id
normal_draft = cls._get_agent_draft(
session=session,
tenant_id=tenant_id,
agent_id=agent.id,
draft_type=AgentConfigDraftType.DRAFT,
account_id=None,
)
if normal_draft is not None and cls._rebase_workflow_only_normal_draft(
agent=agent,
draft=normal_draft,
snapshot=version,
updated_by=account_id,
):
session.flush()
binding.updated_by = account_id
return binding
@@ -1748,6 +1762,47 @@ class AgentComposerService:
stmt = stmt.where(AgentConfigDraft.account_id.is_(None))
return session.scalar(stmt.order_by(AgentConfigDraft.updated_at.desc()).limit(1))
@classmethod
def get_or_create_normal_agent_draft(
cls,
*,
session: Session,
tenant_id: str,
agent: Agent,
created_by: str | None,
) -> AgentConfigDraft:
"""Resolve the shared Preview draft, rebasing inline agents when needed."""
return cls._get_or_create_agent_draft(
session=session,
tenant_id=tenant_id,
agent=agent,
draft_type=AgentConfigDraftType.DRAFT,
account_id=None,
created_by=created_by,
)
@staticmethod
def _rebase_workflow_only_normal_draft(
*,
agent: Agent,
draft: AgentConfigDraft,
snapshot: AgentConfigSnapshot,
updated_by: str | None,
) -> bool:
if (
agent.scope != AgentScope.WORKFLOW_ONLY
or draft.draft_type != AgentConfigDraftType.DRAFT
or draft.account_id is not None
or not agent.active_config_snapshot_id
or draft.base_snapshot_id == agent.active_config_snapshot_id
or snapshot.id != agent.active_config_snapshot_id
):
return False
draft.base_snapshot_id = snapshot.id
draft.config_snapshot = AgentSoulConfig.model_validate(snapshot.config_snapshot_dict)
draft.updated_by = updated_by
return True
@classmethod
def _get_or_create_agent_draft(
cls,
@@ -1767,6 +1822,26 @@ class AgentComposerService:
account_id=account_id,
)
if draft is not None:
if (
agent.scope == AgentScope.WORKFLOW_ONLY
and draft_type == AgentConfigDraftType.DRAFT
and draft.account_id is None
and agent.active_config_snapshot_id
and draft.base_snapshot_id != agent.active_config_snapshot_id
):
active_snapshot = cls._get_version_if_present(
session=session,
tenant_id=tenant_id,
agent_id=agent.id,
version_id=agent.active_config_snapshot_id,
)
if active_snapshot is not None and cls._rebase_workflow_only_normal_draft(
agent=agent,
draft=draft,
snapshot=active_snapshot,
updated_by=agent.updated_by or agent.created_by,
):
session.flush()
return draft
base_snapshot = cls._get_version_if_present(
session=session,
+252 -52
View File
@@ -1,8 +1,11 @@
from __future__ import annotations
import json
from collections.abc import Mapping
from dataclasses import dataclass
from datetime import datetime
from decimal import Decimal
from enum import Enum
from typing import Any
import sqlalchemy as sa
@@ -11,6 +14,7 @@ from sqlalchemy.orm import aliased
from configs import dify_config
from core.app.entities.app_invoke_entities import InvokeFrom
from graphon.enums import WorkflowNodeExecutionStatus
from libs.helper import convert_datetime_to_date, escape_like_pattern, to_timestamp
from models.agent import WorkflowAgentNodeBinding
from models.enums import CreatorUserRole, MessageStatus
@@ -194,11 +198,12 @@ class AgentObservabilityService:
self, *, app: App, agent_id: str, conversation_id: str, params: AgentLogQueryParams
) -> dict[str, Any]:
source_filters = self.resolve_source_filters(params.sources)
rows: list[Message] = []
rows: list[dict[str, Any]] = []
for source_filter in source_filters:
if source_filter.kind in {"all", "webapp"}:
rows.extend(
self._list_webapp_messages(
self.serialize_log_message(message)
for message in self._list_webapp_messages(
app=app,
conversation_id=conversation_id,
params=params,
@@ -216,18 +221,18 @@ class AgentObservabilityService:
)
)
deduped = {message.id: message for message in rows}
sort_column = Message.created_at if params.sort_by == "created_at" else Message.updated_at
deduped = {row["id"]: row for row in rows}
sort_key = "created_at" if params.sort_by == "created_at" else "updated_at"
sorted_rows = sorted(
deduped.values(),
key=lambda message: (getattr(message, sort_column.key), message.id),
key=lambda row: (row[sort_key] or 0, row["id"]),
reverse=params.sort_order != "asc",
)
total = len(sorted_rows)
start = (params.page - 1) * params.limit
end = start + params.limit
return {
"data": [self.serialize_log_message(message) for message in sorted_rows[start:end]],
"data": sorted_rows[start:end],
"page": params.page,
"limit": params.limit,
"total": total,
@@ -284,22 +289,20 @@ class AgentObservabilityService:
workflow_app = aliased(App)
stmt = (
select(
Conversation,
WorkflowNodeExecutionModel.id.label("node_execution_id"),
WorkflowNodeExecutionModel.title.label("node_title"),
WorkflowNodeExecutionModel.status.label("node_status"),
WorkflowNodeExecutionModel.created_by_role.label("node_created_by_role"),
WorkflowNodeExecutionModel.created_by.label("node_created_by"),
WorkflowNodeExecutionModel.created_at.label("node_created_at"),
WorkflowNodeExecutionModel.finished_at.label("node_finished_at"),
workflow_app,
WorkflowAgentNodeBinding.workflow_id,
WorkflowAgentNodeBinding.workflow_version,
WorkflowAgentNodeBinding.node_id,
func.count(sa.distinct(Message.id)).label("message_count"),
func.max(Message.created_at).label("created_at"),
func.max(Message.updated_at).label("updated_at"),
func.sum(sa.case((Message.status == MessageStatus.PAUSED, 1), else_=0)).label("paused_count"),
func.sum(
sa.case((or_(Message.error.is_not(None), Message.status == MessageStatus.ERROR), 1), else_=0)
).label("failed_count"),
)
.select_from(Message)
.join(Conversation, Conversation.id == Message.conversation_id)
.join(WorkflowRun, WorkflowRun.id == Message.workflow_run_id)
.select_from(WorkflowNodeExecutionModel)
.join(WorkflowRun, WorkflowRun.id == WorkflowNodeExecutionModel.workflow_run_id)
.join(
WorkflowAgentNodeBinding,
and_(
@@ -310,40 +313,32 @@ class AgentObservabilityService:
WorkflowAgentNodeBinding.workflow_version == WorkflowRun.version,
),
)
.join(
WorkflowNodeExecutionModel,
and_(
WorkflowNodeExecutionModel.workflow_run_id == WorkflowRun.id,
WorkflowNodeExecutionModel.node_id == WorkflowAgentNodeBinding.node_id,
),
)
.join(workflow_app, workflow_app.id == WorkflowAgentNodeBinding.app_id)
.where(Message.workflow_run_id.is_not(None), Conversation.app_id == WorkflowAgentNodeBinding.app_id)
.group_by(
Conversation.id,
workflow_app.id,
WorkflowAgentNodeBinding.workflow_id,
WorkflowAgentNodeBinding.workflow_version,
WorkflowAgentNodeBinding.node_id,
.where(
WorkflowNodeExecutionModel.tenant_id == app.tenant_id,
WorkflowNodeExecutionModel.app_id == WorkflowAgentNodeBinding.app_id,
WorkflowNodeExecutionModel.workflow_id == WorkflowAgentNodeBinding.workflow_id,
WorkflowNodeExecutionModel.node_id == WorkflowAgentNodeBinding.node_id,
)
)
stmt = self._apply_observability_filters(stmt, params=params, source_filter=source_filter)
stmt = self._apply_workflow_node_filters(stmt, params=params, workflow_app=workflow_app)
stmt = self._apply_workflow_source_filter(stmt, source_filter)
rows = list(self._session.execute(stmt).all())
return [
self._serialize_conversation_log(
conversation=row[0],
message_count=row.message_count,
paused_count=row.paused_count,
failed_count=row.failed_count,
self._serialize_workflow_execution_log(
node_execution_id=row.node_execution_id,
title=row.node_title,
status=row.node_status,
created_by_role=row.node_created_by_role,
created_by=row.node_created_by,
created_at=row.node_created_at,
finished_at=row.node_finished_at,
source=self._serialize_workflow_source(
app=row[1],
app=row[7],
workflow_id=row.workflow_id,
workflow_version=row.workflow_version,
node_id=row.node_id,
),
created_at=row.created_at,
updated_at=row.updated_at,
)
for row in rows
]
@@ -363,10 +358,12 @@ class AgentObservabilityService:
conversation_id: str,
params: AgentLogQueryParams,
source_filter: AgentSourceFilter,
) -> list[Message]:
) -> list[dict[str, Any]]:
workflow_app = aliased(App)
stmt = (
select(Message)
.join(WorkflowRun, WorkflowRun.id == Message.workflow_run_id)
select(WorkflowNodeExecutionModel)
.select_from(WorkflowNodeExecutionModel)
.join(WorkflowRun, WorkflowRun.id == WorkflowNodeExecutionModel.workflow_run_id)
.join(
WorkflowAgentNodeBinding,
and_(
@@ -377,18 +374,23 @@ class AgentObservabilityService:
WorkflowAgentNodeBinding.workflow_version == WorkflowRun.version,
),
)
.join(
WorkflowNodeExecutionModel,
and_(
WorkflowNodeExecutionModel.workflow_run_id == WorkflowRun.id,
WorkflowNodeExecutionModel.node_id == WorkflowAgentNodeBinding.node_id,
),
.join(workflow_app, workflow_app.id == WorkflowAgentNodeBinding.app_id)
.where(
WorkflowNodeExecutionModel.id == conversation_id,
WorkflowNodeExecutionModel.tenant_id == app.tenant_id,
WorkflowNodeExecutionModel.app_id == WorkflowAgentNodeBinding.app_id,
WorkflowNodeExecutionModel.workflow_id == WorkflowAgentNodeBinding.workflow_id,
WorkflowNodeExecutionModel.node_id == WorkflowAgentNodeBinding.node_id,
)
.where(Message.conversation_id == conversation_id)
)
stmt = self._apply_message_filters(stmt, params=params, source_filter=source_filter)
stmt = self._apply_workflow_node_filters(stmt, params=params, workflow_app=workflow_app)
stmt = self._apply_workflow_source_filter(stmt, source_filter)
return list(self._session.scalars(stmt.order_by(Message.created_at.desc(), Message.id.desc())).all())
executions = list(
self._session.scalars(
stmt.order_by(WorkflowNodeExecutionModel.created_at.desc(), WorkflowNodeExecutionModel.id.desc())
).all()
)
return [self.serialize_workflow_node_message(execution) for execution in executions]
def _list_workflow_sources(self, *, app: App, agent_id: str) -> list[dict[str, Any]]:
workflow_app = aliased(App)
@@ -443,6 +445,62 @@ class AgentObservabilityService:
stmt = cls._apply_status_filter(stmt, params.statuses)
return stmt
@classmethod
def _apply_workflow_node_filters(cls, stmt, *, params: AgentLogQueryParams, workflow_app):
if params.start:
stmt = stmt.where(WorkflowNodeExecutionModel.created_at >= params.start)
if params.end:
stmt = stmt.where(WorkflowNodeExecutionModel.created_at < params.end)
if params.keyword:
escaped_keyword = escape_like_pattern(params.keyword)
pattern = f"%{escaped_keyword}%"
stmt = stmt.where(
or_(
WorkflowNodeExecutionModel.inputs.ilike(pattern, escape="\\"),
WorkflowNodeExecutionModel.outputs.ilike(pattern, escape="\\"),
WorkflowNodeExecutionModel.error.ilike(pattern, escape="\\"),
WorkflowNodeExecutionModel.title.ilike(pattern, escape="\\"),
workflow_app.name.ilike(pattern, escape="\\"),
)
)
if params.statuses:
stmt = cls._apply_workflow_node_status_filter(stmt, params.statuses)
return stmt
@staticmethod
def _apply_workflow_node_status_filter(stmt, statuses: tuple[str, ...]):
conditions = []
for status in statuses:
normalized = status.strip().lower()
if normalized in {"success", "normal"}:
conditions.append(WorkflowNodeExecutionModel.status == WorkflowNodeExecutionStatus.SUCCEEDED)
elif normalized in {"failed", "error"}:
conditions.append(
WorkflowNodeExecutionModel.status.in_(
(
WorkflowNodeExecutionStatus.FAILED,
WorkflowNodeExecutionStatus.EXCEPTION,
WorkflowNodeExecutionStatus.STOPPED,
)
)
)
elif normalized == "paused":
conditions.append(
WorkflowNodeExecutionModel.status.in_(
(
WorkflowNodeExecutionStatus.PAUSED,
WorkflowNodeExecutionStatus.PENDING,
WorkflowNodeExecutionStatus.RUNNING,
WorkflowNodeExecutionStatus.RETRY,
)
)
)
else:
raise ValueError(f"Unsupported status: {status}")
if not conditions:
return stmt
return stmt.where(or_(*conditions))
@staticmethod
def _apply_workflow_source_filter(stmt, source_filter: AgentSourceFilter):
if source_filter.app_id:
@@ -505,6 +563,148 @@ class AgentObservabilityService:
"updated_at": to_timestamp(updated_at or conversation.updated_at),
}
@classmethod
def _serialize_workflow_execution_log(
cls,
*,
node_execution_id: str,
title: str,
status: object,
created_by_role: object,
created_by: str,
created_at: datetime,
finished_at: datetime | None,
source: dict[str, Any],
) -> dict[str, Any]:
created_by_role_value = cls._enum_value(created_by_role)
return {
"id": node_execution_id,
"conversation_id": node_execution_id,
"title": title,
"end_user_id": created_by if created_by_role_value == CreatorUserRole.END_USER.value else None,
"message_count": 1,
"user_rate": None,
"operation_rate": None,
"unread": False,
"source": source,
"status": cls._workflow_node_status(status),
"created_at": to_timestamp(created_at),
"updated_at": to_timestamp(finished_at or created_at),
}
@classmethod
def serialize_workflow_node_message(cls, node_execution: WorkflowNodeExecutionModel) -> dict[str, Any]:
inputs = cls._json_mapping(node_execution.inputs)
outputs = cls._json_mapping(node_execution.outputs)
metadata = cls._json_mapping(node_execution.execution_metadata)
agent_log = cls._mapping_value(metadata, "agent_log")
agent_backend = cls._mapping_value(agent_log, "agent_backend")
usage = cls._mapping_value(agent_backend, "usage")
prompt_tokens = cls._int_value(usage.get("prompt_tokens"))
completion_tokens = cls._int_value(usage.get("completion_tokens"))
total_tokens = cls._int_value(usage.get("total_tokens") or metadata.get("total_tokens"))
if not total_tokens:
total_tokens = prompt_tokens + completion_tokens
created_by_role = cls._enum_value(node_execution.created_by_role)
return {
"id": node_execution.id,
"message_id": node_execution.id,
"conversation_id": node_execution.id,
"query": cls._workflow_node_query(inputs, fallback=node_execution.title),
"answer": cls._workflow_node_answer(outputs),
"status": cls._workflow_node_status(node_execution.status),
"error": node_execution.error,
"from_end_user_id": (
node_execution.created_by if created_by_role == CreatorUserRole.END_USER.value else None
),
"from_account_id": (
node_execution.created_by if created_by_role == CreatorUserRole.ACCOUNT.value else None
),
"message_tokens": prompt_tokens,
"answer_tokens": completion_tokens,
"total_tokens": total_tokens,
"total_price": str(usage.get("total_price") or metadata.get("total_price") or Decimal(0)),
"currency": str(usage.get("currency") or metadata.get("currency") or ""),
"latency": float(usage.get("latency") or node_execution.elapsed_time or 0),
"created_at": to_timestamp(node_execution.created_at),
"updated_at": to_timestamp(node_execution.finished_at or node_execution.created_at),
}
@staticmethod
def _json_mapping(value: object) -> Mapping[str, Any]:
if isinstance(value, Mapping):
return value
if not isinstance(value, str) or not value:
return {}
try:
parsed = json.loads(value)
except (TypeError, ValueError):
return {}
return parsed if isinstance(parsed, Mapping) else {}
@staticmethod
def _mapping_value(value: Mapping[str, Any], key: str) -> Mapping[str, Any]:
nested = value.get(key)
return nested if isinstance(nested, Mapping) else {}
@staticmethod
def _enum_value(value: object) -> str:
return str(value.value) if isinstance(value, Enum) else str(value)
@staticmethod
def _int_value(value: object) -> int:
if not isinstance(value, (str, int, float, Decimal)):
return 0
try:
return int(value)
except (TypeError, ValueError):
return 0
@classmethod
def _workflow_node_query(cls, inputs: Mapping[str, Any], *, fallback: str) -> str:
request_data = cls._mapping_value(inputs, "agent_backend_request")
composition = cls._mapping_value(request_data, "composition")
layers = composition.get("layers")
prompts: list[str] = []
if isinstance(layers, list):
for layer_name in ("workflow_node_job_prompt", "workflow_user_prompt"):
for layer in layers:
if not isinstance(layer, Mapping) or layer.get("name") != layer_name:
continue
config = cls._mapping_value(layer, "config")
user_prompt = config.get("user")
if isinstance(user_prompt, str) and user_prompt.strip():
prompts.append(user_prompt.strip())
return "\n\n".join(prompts) or fallback
@staticmethod
def _workflow_node_answer(outputs: Mapping[str, Any]) -> str:
for key in ("output", "text", "answer"):
value = outputs.get(key)
if isinstance(value, str):
return value
return json.dumps(outputs, ensure_ascii=False) if outputs else ""
@classmethod
def _workflow_node_status(cls, status: object) -> str:
value = cls._enum_value(status)
if value in {
WorkflowNodeExecutionStatus.FAILED.value,
WorkflowNodeExecutionStatus.EXCEPTION.value,
WorkflowNodeExecutionStatus.STOPPED.value,
}:
return "failed"
if value in {
WorkflowNodeExecutionStatus.PAUSED.value,
WorkflowNodeExecutionStatus.PENDING.value,
WorkflowNodeExecutionStatus.RUNNING.value,
WorkflowNodeExecutionStatus.RETRY.value,
}:
return "paused"
return "success"
@staticmethod
def _conversation_status(*, paused_count: int, failed_count: int) -> str:
if paused_count:
+113 -35
View File
@@ -430,7 +430,11 @@ class AgentRosterService:
agent.active_config_has_model = agent_soul_has_model(soul)
agent.active_config_is_published = False
self._session.flush()
self._get_or_create_agent_app_debug_conversation(agent=agent, account_id=account_id)
self._get_or_create_agent_app_debug_conversation(
agent=agent,
account_id=account_id,
draft_type=AgentConfigDraftType.DEBUG_BUILD,
)
return agent
def create_hidden_backing_app_for_workflow_agent(
@@ -527,7 +531,11 @@ class AgentRosterService:
self._session.flush()
return backing_app.id
def _get_or_create_agent_app_debug_conversation(self, *, agent: Agent, account_id: str) -> str:
def _get_or_create_agent_app_debug_conversation(
self, *, agent: Agent, account_id: str, draft_type: AgentConfigDraftType
) -> str:
"""Return the editor's conversation for one Agent draft surface."""
backing_app_id = self._ensure_workflow_agent_backing_app(agent=agent, account_id=account_id)
if not backing_app_id:
raise AgentNotFoundError()
@@ -537,6 +545,7 @@ class AgentRosterService:
AgentDebugConversation.tenant_id == agent.tenant_id,
AgentDebugConversation.agent_id == agent.id,
AgentDebugConversation.account_id == account_id,
AgentDebugConversation.draft_type == draft_type,
)
)
if mapping is not None:
@@ -570,6 +579,7 @@ class AgentRosterService:
agent_id=agent.id,
app_id=backing_app_id,
account_id=account_id,
draft_type=draft_type,
conversation_id=conversation_id,
)
)
@@ -577,9 +587,15 @@ class AgentRosterService:
return conversation_id
def get_or_create_agent_app_debug_conversation_id(
self, *, tenant_id: str, agent_id: str, account_id: str, commit: bool = True
self,
*,
tenant_id: str,
agent_id: str,
account_id: str,
draft_type: AgentConfigDraftType = AgentConfigDraftType.DEBUG_BUILD,
commit: bool = True,
) -> str:
"""Return the current editor's debug conversation for an Agent App."""
"""Return the current editor's Build or Preview conversation for an Agent App."""
agent = self._session.scalar(
select(Agent).where(
@@ -591,13 +607,24 @@ class AgentRosterService:
if agent is None:
raise AgentNotFoundError()
conversation_id = self._get_or_create_agent_app_debug_conversation(agent=agent, account_id=account_id)
conversation_id = self._get_or_create_agent_app_debug_conversation(
agent=agent,
account_id=account_id,
draft_type=draft_type,
)
if commit:
self._session.commit()
return conversation_id
def load_agent_app_debug_conversation_id(self, *, tenant_id: str, agent_id: str, account_id: str) -> str | None:
"""Return the current editor's existing debug conversation without creating or repairing rows."""
def load_agent_app_debug_conversation_id(
self,
*,
tenant_id: str,
agent_id: str,
account_id: str,
draft_type: AgentConfigDraftType = AgentConfigDraftType.DEBUG_BUILD,
) -> str | None:
"""Return the editor's existing scoped conversation without creating or repairing rows."""
return self._session.scalar(
select(Conversation.id)
@@ -606,6 +633,7 @@ class AgentRosterService:
AgentDebugConversation.tenant_id == tenant_id,
AgentDebugConversation.agent_id == agent_id,
AgentDebugConversation.account_id == account_id,
AgentDebugConversation.draft_type == draft_type,
AgentDebugConversation.app_id == Conversation.app_id,
Conversation.from_source == ConversationFromSource.CONSOLE,
Conversation.from_account_id == account_id,
@@ -626,16 +654,24 @@ class AgentRosterService:
)
def refresh_agent_app_debug_conversation_id(
self, *, tenant_id: str, agent_id: str, account_id: str, commit: bool = True
self,
*,
tenant_id: str,
agent_id: str,
account_id: str,
draft_type: AgentConfigDraftType = AgentConfigDraftType.DEBUG_BUILD,
) -> str:
"""Start a new console debug conversation for the current Agent App editor.
"""Start a new scoped console conversation for the current Agent App editor.
If this account already has a debug conversation mapping, the previous
conversation is abandoned first: any ACTIVE conversation-owned Agent
runtime sessions for that old conversation are sent through best-effort
backend cleanup and then retired locally even when enqueueing fails.
The debug mapping is then repointed to the freshly created
conversation.
If this account already has a mapping for the requested draft surface, the previous
conversation is abandoned after the replacement mapping is committed: any ACTIVE
conversation-owned Agent runtime sessions for that old conversation are sent through
best-effort backend cleanup and then retired locally even when enqueueing fails. This
order prevents a failed database commit from retiring the still-current runtime session.
The other draft surface is left untouched.
A user and draft surface own one current mapping. If new-conversation requests overlap,
the last committed rotation becomes current and earlier response IDs cannot be continued.
"""
agent = self._session.scalar(
@@ -658,11 +694,13 @@ class AgentRosterService:
app_id=backing_app_id,
account_id=account_id,
)
previous_conversation: tuple[str, str] | None = None
mapping = self._session.scalar(
select(AgentDebugConversation).where(
AgentDebugConversation.tenant_id == tenant_id,
AgentDebugConversation.agent_id == agent_id,
AgentDebugConversation.account_id == account_id,
AgentDebugConversation.draft_type == draft_type,
)
)
if mapping is None:
@@ -672,6 +710,7 @@ class AgentRosterService:
agent_id=agent_id,
app_id=backing_app_id,
account_id=account_id,
draft_type=draft_type,
conversation_id=conversation_id,
)
)
@@ -679,18 +718,22 @@ class AgentRosterService:
previous_app_id = mapping.app_id
previous_conversation_id = mapping.conversation_id
if previous_conversation_id:
self._cleanup_debug_conversation_runtime_sessions(
tenant_id=tenant_id,
agent_id=agent_id,
account_id=account_id,
app_id=previous_app_id or backing_app_id,
conversation_id=previous_conversation_id,
)
previous_conversation = (previous_app_id or backing_app_id, previous_conversation_id)
mapping.app_id = backing_app_id
mapping.conversation_id = conversation_id
self._session.flush()
if commit:
self._session.commit()
self._session.commit()
if previous_conversation:
previous_app_id, previous_conversation_id = previous_conversation
self._cleanup_debug_conversation_runtime_sessions(
tenant_id=tenant_id,
agent_id=agent_id,
account_id=account_id,
draft_type=draft_type,
app_id=previous_app_id,
conversation_id=previous_conversation_id,
)
return conversation_id
def _cleanup_debug_conversation_runtime_sessions(
@@ -699,11 +742,12 @@ class AgentRosterService:
tenant_id: str,
agent_id: str,
account_id: str,
draft_type: AgentConfigDraftType,
app_id: str,
conversation_id: str,
) -> None:
session_store = AgentAppRuntimeSessionStore()
try:
session_store = AgentAppRuntimeSessionStore()
stored_sessions = session_store.list_active_sessions_for_conversation(
tenant_id=tenant_id,
app_id=app_id,
@@ -727,7 +771,8 @@ class AgentRosterService:
session_snapshot=stored_session.session_snapshot,
runtime_layer_specs=stored_session.runtime_layer_specs,
idempotency_key=(
f"{tenant_id}:{agent_id}:{account_id}:{conversation_id}:debug-session-cleanup:"
f"{tenant_id}:{agent_id}:{account_id}:{draft_type.value}:{conversation_id}:"
"debug-session-cleanup:"
f"{stored_session.scope.agent_id}:"
f"{stored_session.scope.agent_config_snapshot_id or 'no-config'}:"
f"{stored_session.backend_run_id or 'no-run'}"
@@ -738,6 +783,7 @@ class AgentRosterService:
"conversation_id": stored_session.scope.conversation_id,
"agent_id": stored_session.scope.agent_id,
"agent_config_snapshot_id": stored_session.scope.agent_config_snapshot_id,
"draft_type": draft_type.value,
"previous_agent_backend_run_id": stored_session.backend_run_id,
},
)
@@ -772,9 +818,14 @@ class AgentRosterService:
)
def load_or_create_agent_app_debug_conversation_ids_by_agent_id(
self, *, tenant_id: str, agents: list[Agent], account_id: str
self,
*,
tenant_id: str,
agents: list[Agent],
account_id: str,
draft_type: AgentConfigDraftType = AgentConfigDraftType.DEBUG_BUILD,
) -> dict[str, str]:
"""Return per-account debug conversations for a page of Agent Apps."""
"""Return per-account scoped conversations for a page of Agent Apps."""
conversation_ids_by_agent_id: dict[str, str] = {}
changed = False
@@ -784,6 +835,7 @@ class AgentRosterService:
conversation_ids_by_agent_id[agent.id] = self._get_or_create_agent_app_debug_conversation(
agent=agent,
account_id=account_id,
draft_type=draft_type,
)
changed = True
if changed:
@@ -866,16 +918,14 @@ class AgentRosterService:
raise AgentNotFoundError()
return app
def get_agent_runtime_app_model(self, *, tenant_id: str, agent_id: str) -> App:
"""Resolve the App that backs an Agent runtime surface.
def _get_runtime_resolvable_agent(self, *, tenant_id: str, agent_id: str) -> Agent | None:
"""Load an Agent that is eligible to resolve to a runtime backing App.
Roster Agents use their public Agent App. Workflow-only Agents use a
hidden Agent App stored in ``backing_app_id`` so console chat/logs can
reuse the app runtime without exposing the resource in workspace app
lists.
Shared by the runtime resolver and the read-only authorization resolver
so both agree on what counts as a resolvable Agent.
"""
agent = self._session.scalar(
return self._session.scalar(
select(Agent)
.where(
Agent.tenant_id == tenant_id,
@@ -893,6 +943,34 @@ class AgentRosterService:
)
.limit(1)
)
def peek_authz_app_id(self, *, tenant_id: str, agent_id: str) -> str | None:
"""Resolve the App id whose access policy governs an Agent.
Roster Agents are governed by their own Agent App, while workflow-only
Agents are governed by their parent workflow App: the hidden runtime
backing App never receives a resource access policy, so it must not be
used for authorization. Stays read-only unlike
:meth:`get_agent_runtime_app_model`, this never materializes the hidden
backing App. Returns ``None`` when the Agent does not resolve, leaving
the caller to decide how to treat it.
"""
agent = self._get_runtime_resolvable_agent(tenant_id=tenant_id, agent_id=agent_id)
if agent is None:
return None
return agent.app_id
def get_agent_runtime_app_model(self, *, tenant_id: str, agent_id: str) -> App:
"""Resolve the App that backs an Agent runtime surface.
Roster Agents use their public Agent App. Workflow-only Agents use a
hidden Agent App stored in ``backing_app_id`` so console chat/logs can
reuse the app runtime without exposing the resource in workspace app
lists.
"""
agent = self._get_runtime_resolvable_agent(tenant_id=tenant_id, agent_id=agent_id)
if agent is None:
raise AgentNotFoundError()
should_commit_backing_app = agent.scope == AgentScope.WORKFLOW_ONLY and not agent.backing_app_id
+1
View File
@@ -92,6 +92,7 @@ class AgentToolInnerService:
conversation_id=request.caller.conversation_id,
)
)
transformed_messages, _ = ToolEngine.collect_agent_messages(transformed_messages)
except ToolProviderNotFoundError as exc:
raise AgentToolInnerServiceError(
error_code="agent_tool_declaration_not_found",
+26
View File
@@ -19,6 +19,7 @@ from configs import dify_config
from constants.dsl_version import CURRENT_APP_DSL_VERSION
from core.file import remote_fetcher
from core.plugin.entities.plugin import PluginDependency
from core.rbac import RBACPermission
from core.trigger.constants import (
TRIGGER_PLUGIN_NODE_TYPE,
TRIGGER_SCHEDULE_NODE_TYPE,
@@ -43,7 +44,9 @@ from services.agent.dsl_service import AgentDslService, AgentPackage
from services.agent.workflow_publish_service import WorkflowAgentPublishService
from services.dsl_content import DSL_MAX_SIZE, dsl_content_size
from services.dsl_version import check_version_compatibility
from services.enterprise.rbac_service import RBACService
from services.entities.dsl_entities import CheckDependenciesResult, DslImportWarning, ImportMode, ImportStatus
from services.errors.account import NoPermissionError
from services.errors.app import WorkflowNotFoundError
from services.plugin.dependencies_analysis import DependenciesAnalysisService
from services.workflow_draft_variable_service import WorkflowDraftVariableService
@@ -301,6 +304,9 @@ class AppDslService:
error=f"Invalid YAML format: {str(e)}",
)
except NoPermissionError:
raise
except Exception as e:
logger.exception("Failed to import app")
return Import(
@@ -364,6 +370,9 @@ class AppDslService:
warnings=self._warnings,
)
except NoPermissionError:
raise
except Exception as e:
logger.exception("Error confirming import")
return Import(
@@ -395,6 +404,21 @@ class AppDslService:
leaked_dependencies=leaked_dependencies,
)
@staticmethod
def _ensure_agent_manage_permission(account: Account) -> None:
"""Importing an Agent DSL creates a roster Agent, which requires ``agent.manage``."""
if not dify_config.RBAC_ENABLED:
return
if account.current_tenant_id is None:
raise ValueError("Current tenant is not set")
allowed = RBACService.CheckAccess.check(
account.current_tenant_id,
account.id,
scene=RBACPermission.AGENT_MANAGE,
)
if not allowed:
raise NoPermissionError("Agent management permission is required to import an Agent App")
def _create_or_update_app(
self,
*,
@@ -415,6 +439,8 @@ class AppDslService:
if not app_mode:
raise ValueError("loss app mode")
app_mode = AppMode(app_mode)
if app_mode == AppMode.AGENT:
self._ensure_agent_manage_permission(account)
# Set icon type
icon_type_value = icon_type or app_data.get("icon_type")
+7 -1
View File
@@ -217,12 +217,18 @@ class BillingService:
return _billing_info_adapter.validate_python(billing_info)
@classmethod
def get_vector_space(cls, tenant_id: str) -> _VectorSpaceQuota:
def get_vector_space(cls, tenant_id: str, bypass_cache: bool = False) -> _VectorSpaceQuota:
params = {"tenant_id": tenant_id}
if bypass_cache:
params["bypass_cache"] = "true"
return _vector_space_quota_adapter.validate_python(
cls._send_request("GET", "/subscription/vector-space", params=params)
)
@classmethod
def invalidate_vector_space_cache(cls, tenant_id: str) -> None:
cls.get_vector_space(tenant_id, bypass_cache=True)
@classmethod
def get_tenant_feature_plan_usage_info(cls, tenant_id: str):
"""Deprecated: Use get_quota_info instead."""
+10 -2
View File
@@ -1974,7 +1974,10 @@ class DocumentService:
if data_source_info and "upload_file_id" in data_source_info:
file_id = data_source_info["upload_file_id"]
document_was_deleted.send(
document.id, dataset_id=document.dataset_id, doc_form=document.doc_form, file_id=file_id
document.id,
dataset_id=document.dataset_id,
doc_form=document.doc_form,
file_id=file_id,
)
session.delete(document)
@@ -2013,7 +2016,12 @@ class DocumentService:
# Dispatch cleanup task after commit to avoid lock contention
# Task cleans up segments, files, and vector indexes
if deleted_document_ids and doc_form is not None:
batch_clean_document_task.delay(deleted_document_ids, dataset_ref.dataset_id, doc_form, file_ids)
batch_clean_document_task.delay(
deleted_document_ids,
dataset_ref.dataset_id,
doc_form,
file_ids,
)
@staticmethod
def rename_document(dataset_id: str, document_id: str, name: str, session: Session) -> Document:
+10 -8
View File
@@ -5,6 +5,7 @@ from typing import Any
import httpx
from configs import dify_config
from core.helper.trace_id_helper import generate_traceparent_header
from services.errors.enterprise import (
EnterpriseAPIBadRequestError,
@@ -96,12 +97,14 @@ class BaseRequest:
logger.debug("Failed to generate traceparent header", exc_info=True)
with httpx.Client(mounts=mounts) as client:
# IMPORTANT:
# - In httpx, passing timeout=None disables timeouts (infinite) and overrides the library default.
# - To preserve httpx's default timeout behavior for existing call sites, only pass the kwarg when set.
request_kwargs: dict[str, Any] = {"json": json, "params": params, "headers": headers}
if timeout is not None:
request_kwargs["timeout"] = timeout
# Callers that pass an explicit timeout keep it; everyone else gets the
# configured budget rather than httpx's implicit 5s default.
request_kwargs: dict[str, Any] = {
"json": json,
"params": params,
"headers": headers,
"timeout": timeout if timeout is not None else dify_config.ENTERPRISE_REQUEST_TIMEOUT,
}
response = client.request(method, url, **request_kwargs)
@@ -206,9 +209,8 @@ class EnterpriseRequest(BaseRequest):
"json": json,
"params": params,
"headers": {"Content-Type": "application/json", cls.secret_key_header: cls.secret_key, **inner_headers},
"timeout": timeout if timeout is not None else dify_config.ENTERPRISE_RBAC_REQUEST_TIMEOUT,
}
if timeout is not None:
request_kwargs["timeout"] = timeout
response = client.request(method, url, **request_kwargs)
if not response.is_success:
cls._handle_error_response(response)
+3
View File
@@ -330,6 +330,7 @@ _LEGACY_WORKSPACE_OWNER_KEYS: list[str] = [
"snippets.management",
"tool.manage",
"mcp.manage",
"agent.manage",
]
_LEGACY_WORKSPACE_ADMIN_KEYS: list[str] = [
@@ -357,6 +358,7 @@ _LEGACY_WORKSPACE_ADMIN_KEYS: list[str] = [
"snippets.management",
"tool.manage",
"mcp.manage",
"agent.manage",
]
_LEGACY_WORKSPACE_EDITOR_KEYS: list[str] = [
@@ -371,6 +373,7 @@ _LEGACY_WORKSPACE_EDITOR_KEYS: list[str] = [
"dataset.external.connect",
"snippets.create_and_modify",
"tool.manage",
"agent.manage",
]
_LEGACY_WORKSPACE_NORMAL_KEYS: list[str] = [
+13 -1
View File
@@ -93,8 +93,20 @@ class ExternalDatasetService:
raise ValueError(f"invalid endpoint: {endpoint} must start with http:// or https://")
else:
raise ValueError(f"invalid endpoint: {endpoint}")
# Send a minimal body shaped like the External Knowledge API retrieval contract so providers
# that require a JSON payload (e.g. RAGFlow) accept the validation probe instead of rejecting
# a body-less POST. Mirrors the request built in fetch_external_knowledge_retrieval.
validation_payload = {
"knowledge_id": "",
"query": "",
"retrieval_setting": {"top_k": 1, "score_threshold": 0.0},
}
try:
response = ssrf_proxy.post(endpoint, headers={"Authorization": f"Bearer {api_key}"})
response = ssrf_proxy.post(
endpoint,
headers={"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"},
data=json.dumps(validation_payload),
)
except Exception as e:
raise ValueError(f"failed to connect to the endpoint: {endpoint}") from e
if response.status_code == 502:
+2
View File
@@ -186,6 +186,7 @@ class SystemFeatureModel(FeatureResponseModel):
enable_learn_app: bool = True
enable_step_by_step_tour: bool = False
rbac_enabled: bool = False
knowledge_fs_enabled: bool = False
class FeatureService:
@@ -289,6 +290,7 @@ class FeatureService:
system_features.enable_learn_app = dify_config.ENABLE_LEARN_APP
system_features.webapp_auth.allow_public_access = dify_config.WEBAPP_PUBLIC_ACCESS_ENABLED
system_features.enable_step_by_step_tour = dify_config.ENABLE_STEP_BY_STEP_TOUR
system_features.knowledge_fs_enabled = dify_config.KNOWLEDGE_FS_ENABLED
@classmethod
def _fulfill_trial_models_from_env(cls) -> list[str]:
+23
View File
@@ -141,6 +141,29 @@ class FileService:
blob = storage.load_once(upload_file_key)
return base64.b64encode(blob).decode()
def get_file_presigned_url(self, *, file_id: str, tenant_id: str) -> str:
"""Generate a direct storage URL for a tenant-owned upload file."""
with self._session_maker(expire_on_commit=False) as session:
upload_file = session.scalar(
select(UploadFile)
.where(
UploadFile.id == file_id,
UploadFile.tenant_id == tenant_id,
)
.limit(1)
)
if upload_file is None:
raise NotFound("File not found")
file_key = upload_file.key
content_type = upload_file.mime_type
return storage.generate_presigned_url(
file_key,
expires_in=dify_config.FILES_ACCESS_TIMEOUT,
content_type=content_type,
)
def upload_text(self, text: str, text_name: str, user_id: str, tenant_id: str) -> UploadFile:
if len(text_name) > 200:
text_name = text_name[:200]
+502
View File
@@ -0,0 +1,502 @@
"""Product-facing KnowledgeFS operation and authorization declarations.
This registry is Dify's explicit Console surface. Transport concerns live in
knowledge_fs_proxy so contract review does not require reading proxy mechanics.
"""
from __future__ import annotations
from typing import Final, Literal, NamedTuple
from core.rbac import RBACPermission
type KnowledgeFSMethod = Literal["DELETE", "GET", "PATCH", "POST", "PUT"]
type KnowledgeFSResponseKind = Literal["binary", "buffered", "stream"]
type KnowledgeFSRequiredScope = Literal["knowledge-spaces:read", "knowledge-spaces:write"]
type KnowledgeFSLegacyRole = Literal["reader", "dataset_editor", "admin"]
type KnowledgeFSErrorStatusMap = tuple[tuple[int, int], ...]
class KnowledgeFSOperation(NamedTuple):
operation_id: str
method: KnowledgeFSMethod
path: str
response_kind: KnowledgeFSResponseKind
required_scope: KnowledgeFSRequiredScope
rbac_permission: RBACPermission
legacy_role: KnowledgeFSLegacyRole
max_response_bytes: int
request_headers: tuple[str, ...]
response_headers: tuple[str, ...]
response_media_types: tuple[str, ...]
error_status_map: KnowledgeFSErrorStatusMap
def _console_operation(
operation_id: str,
method: KnowledgeFSMethod,
path: str,
*,
rbac_permission: RBACPermission,
legacy_role: KnowledgeFSLegacyRole,
max_response_bytes: int = 1_048_576,
request_headers: tuple[str, ...] = ("x-trace-id",),
response_kind: KnowledgeFSResponseKind = "buffered",
response_media_types: tuple[str, ...] = ("application/json",),
error_status_map: KnowledgeFSErrorStatusMap = ((401, 502), (403, 403)),
) -> KnowledgeFSOperation:
"""Declare one contract-pinned operation with an explicit Dify authorization policy."""
is_read = method == "GET"
return KnowledgeFSOperation(
operation_id=operation_id,
method=method,
path=path,
response_kind=response_kind,
required_scope="knowledge-spaces:read" if is_read else "knowledge-spaces:write",
rbac_permission=rbac_permission,
legacy_role=legacy_role,
max_response_bytes=max_response_bytes,
request_headers=request_headers,
response_headers=("x-trace-id",),
response_media_types=response_media_types,
error_status_map=error_status_map,
)
def _dataset_read_operation(operation_id: str, path: str) -> KnowledgeFSOperation:
"""Declare a dataset-readable buffered JSON operation."""
return _console_operation(
operation_id,
"GET",
path,
rbac_permission=RBACPermission.DATASET_READONLY,
legacy_role="reader",
)
def _dataset_edit_operation(
operation_id: str,
method: KnowledgeFSMethod,
path: str,
*,
request_headers: tuple[str, ...] = ("x-trace-id",),
) -> KnowledgeFSOperation:
"""Declare a dataset-editable buffered JSON operation."""
return _console_operation(
operation_id,
method,
path,
rbac_permission=RBACPermission.DATASET_EDIT,
legacy_role="dataset_editor",
request_headers=request_headers,
)
def _external_source_operation(
operation_id: str,
method: KnowledgeFSMethod,
path: str,
*,
request_headers: tuple[str, ...] = ("x-trace-id",),
) -> KnowledgeFSOperation:
"""Declare a source-connection operation restricted to dataset editors."""
return _console_operation(
operation_id,
method,
path,
rbac_permission=RBACPermission.DATASET_EXTERNAL_CONNECT,
legacy_role="dataset_editor",
request_headers=request_headers,
)
KNOWLEDGE_FS_CONSOLE_OPERATIONS: Final[tuple[KnowledgeFSOperation, ...]] = (
_console_operation(
operation_id="listKnowledgeSpaces",
method="GET",
path="knowledge-spaces",
rbac_permission=RBACPermission.DATASET_READONLY,
legacy_role="reader",
),
_console_operation(
operation_id="createKnowledgeSpace",
method="POST",
path="knowledge-spaces",
rbac_permission=RBACPermission.DATASET_CREATE_AND_MANAGEMENT,
legacy_role="dataset_editor",
),
_console_operation(
operation_id="getKnowledgeSpacesById",
method="GET",
path="knowledge-spaces/{id}",
rbac_permission=RBACPermission.DATASET_READONLY,
legacy_role="reader",
),
_dataset_edit_operation("patchKnowledgeSpacesById", "PATCH", "knowledge-spaces/{id}"),
_dataset_edit_operation(
"deleteKnowledgeSpacesById",
"DELETE",
"knowledge-spaces/{id}",
request_headers=("idempotency-key", "x-trace-id"),
),
_dataset_read_operation("getKnowledgeSpacesByIdStats", "knowledge-spaces/{id}/stats"),
_console_operation(
operation_id="getKnowledgeSpacesByIdAccessPolicy",
method="GET",
path="knowledge-spaces/{id}/access-policy",
rbac_permission=RBACPermission.DATASET_READONLY,
legacy_role="reader",
),
_console_operation(
operation_id="patchKnowledgeSpacesByIdAccessPolicy",
method="PATCH",
path="knowledge-spaces/{id}/access-policy",
rbac_permission=RBACPermission.DATASET_ACCESS_CONFIG,
legacy_role="admin",
),
_console_operation(
operation_id="getSourceProviders",
method="GET",
path="source-providers",
rbac_permission=RBACPermission.DATASET_EXTERNAL_CONNECT,
legacy_role="dataset_editor",
),
_console_operation(
operation_id="getKnowledgeSpacesByIdSourceConnections",
method="GET",
path="knowledge-spaces/{id}/source-connections",
rbac_permission=RBACPermission.DATASET_EXTERNAL_CONNECT,
legacy_role="dataset_editor",
),
_console_operation(
operation_id="postKnowledgeSpacesByIdSourceConnections",
method="POST",
path="knowledge-spaces/{id}/source-connections",
rbac_permission=RBACPermission.DATASET_EXTERNAL_CONNECT,
legacy_role="dataset_editor",
),
_external_source_operation(
"postKnowledgeSpacesByIdSourceConnectionsOauth",
"POST",
"knowledge-spaces/{id}/source-connections/oauth",
),
_external_source_operation("postSourceOauthCallback", "POST", "source-oauth/callback"),
_external_source_operation(
"getKnowledgeSpacesByIdSourceConnectionsByConnectionId",
"GET",
"knowledge-spaces/{id}/source-connections/{connectionId}",
),
_external_source_operation(
"deleteKnowledgeSpacesByIdSourceConnectionsByConnectionId",
"DELETE",
"knowledge-spaces/{id}/source-connections/{connectionId}",
),
_console_operation(
operation_id="postKnowledgeSpacesByIdSourceConnectionsByConnectionIdRefresh",
method="POST",
path="knowledge-spaces/{id}/source-connections/{connectionId}/refresh",
rbac_permission=RBACPermission.DATASET_EXTERNAL_CONNECT,
legacy_role="dataset_editor",
),
_console_operation(
operation_id="getKnowledgeSpacesByIdSources",
method="GET",
path="knowledge-spaces/{id}/sources",
rbac_permission=RBACPermission.DATASET_READONLY,
legacy_role="reader",
),
_console_operation(
operation_id="postKnowledgeSpacesByIdSources",
method="POST",
path="knowledge-spaces/{id}/sources",
rbac_permission=RBACPermission.DATASET_EXTERNAL_CONNECT,
legacy_role="dataset_editor",
),
_external_source_operation(
"getKnowledgeSpacesByIdSourcesBySourceId",
"GET",
"knowledge-spaces/{id}/sources/{sourceId}",
),
_external_source_operation(
"patchKnowledgeSpacesByIdSourcesBySourceId",
"PATCH",
"knowledge-spaces/{id}/sources/{sourceId}",
),
_external_source_operation(
"deleteKnowledgeSpacesByIdSourcesBySourceId",
"DELETE",
"knowledge-spaces/{id}/sources/{sourceId}",
request_headers=("idempotency-key", "x-trace-id"),
),
_external_source_operation(
"putKnowledgeSpacesByIdSourcesBySourceIdCredentials",
"PUT",
"knowledge-spaces/{id}/sources/{sourceId}/credentials",
),
_external_source_operation(
"deleteKnowledgeSpacesByIdSourcesBySourceIdCredentials",
"DELETE",
"knowledge-spaces/{id}/sources/{sourceId}/credentials",
),
_external_source_operation(
"postKnowledgeSpacesByIdSourcesBySourceIdSync",
"POST",
"knowledge-spaces/{id}/sources/{sourceId}/sync",
request_headers=("idempotency-key", "x-trace-id"),
),
_console_operation(
operation_id="postKnowledgeSpacesByIdSourcesBySourceIdCrawlPreview",
method="POST",
path="knowledge-spaces/{id}/sources/{sourceId}/crawl-preview",
rbac_permission=RBACPermission.DATASET_EXTERNAL_CONNECT,
legacy_role="dataset_editor",
request_headers=("idempotency-key", "x-trace-id"),
),
_external_source_operation(
"postKnowledgeSpacesByIdSourcesBySourceIdWorkflowImports",
"POST",
"knowledge-spaces/{id}/sources/{sourceId}/workflow-imports",
request_headers=("idempotency-key", "x-trace-id"),
),
_external_source_operation(
"getKnowledgeSpacesByIdSourcesBySourceIdPages",
"GET",
"knowledge-spaces/{id}/sources/{sourceId}/pages",
),
_external_source_operation(
"getKnowledgeSpacesByIdSourcesBySourceIdFiles",
"GET",
"knowledge-spaces/{id}/sources/{sourceId}/files",
),
_external_source_operation(
"postKnowledgeSpacesByIdSourcesBySourceIdCrawl",
"POST",
"knowledge-spaces/{id}/sources/{sourceId}/crawl",
),
_external_source_operation(
"postKnowledgeSpacesByIdSourcesBySourceIdImport",
"POST",
"knowledge-spaces/{id}/sources/{sourceId}/import",
),
_external_source_operation(
"postKnowledgeSpacesByIdSourcesBySourceIdTest",
"POST",
"knowledge-spaces/{id}/sources/{sourceId}/test",
),
_external_source_operation(
"postKnowledgeSpacesByIdSourcesBySourceIdImportFiles",
"POST",
"knowledge-spaces/{id}/sources/{sourceId}/import-files",
),
_external_source_operation(
"postKnowledgeSpacesByIdSourcesBulk",
"POST",
"knowledge-spaces/{id}/sources/bulk",
request_headers=("idempotency-key", "x-trace-id"),
),
_external_source_operation(
"getKnowledgeSpacesByIdSourceWorkflows",
"GET",
"knowledge-spaces/{id}/source-workflows",
),
_console_operation(
operation_id="getKnowledgeSpacesByIdSourceWorkflowsByRunId",
method="GET",
path="knowledge-spaces/{id}/source-workflows/{runId}",
rbac_permission=RBACPermission.DATASET_EXTERNAL_CONNECT,
legacy_role="dataset_editor",
),
_external_source_operation(
"getKnowledgeSpacesByIdSourceWorkflowsByRunIdBulkItems",
"GET",
"knowledge-spaces/{id}/source-workflows/{runId}/bulk-items",
),
_console_operation(
operation_id="getKnowledgeSpacesByIdSourceWorkflowsByRunIdPages",
method="GET",
path="knowledge-spaces/{id}/source-workflows/{runId}/pages",
rbac_permission=RBACPermission.DATASET_EXTERNAL_CONNECT,
legacy_role="dataset_editor",
),
_console_operation(
operation_id="postKnowledgeSpacesByIdSourceWorkflowsByRunIdCancel",
method="POST",
path="knowledge-spaces/{id}/source-workflows/{runId}/cancel",
rbac_permission=RBACPermission.DATASET_EXTERNAL_CONNECT,
legacy_role="dataset_editor",
),
_console_operation(
operation_id="postKnowledgeSpacesByIdSourceWorkflowsByRunIdRetry",
method="POST",
path="knowledge-spaces/{id}/source-workflows/{runId}/retry",
rbac_permission=RBACPermission.DATASET_EXTERNAL_CONNECT,
legacy_role="dataset_editor",
),
_console_operation(
operation_id="postKnowledgeSpacesByIdSourceWorkflowsByRunIdSelection",
method="POST",
path="knowledge-spaces/{id}/source-workflows/{runId}/selection",
rbac_permission=RBACPermission.DATASET_EXTERNAL_CONNECT,
legacy_role="dataset_editor",
request_headers=("idempotency-key", "x-trace-id"),
),
_console_operation(
operation_id="getKnowledgeSpacesByIdSourcesBySourceIdSyncPolicy",
method="GET",
path="knowledge-spaces/{id}/sources/{sourceId}/sync-policy",
rbac_permission=RBACPermission.DATASET_READONLY,
legacy_role="reader",
),
_console_operation(
operation_id="putKnowledgeSpacesByIdSourcesBySourceIdSyncPolicy",
method="PUT",
path="knowledge-spaces/{id}/sources/{sourceId}/sync-policy",
rbac_permission=RBACPermission.DATASET_EDIT,
legacy_role="dataset_editor",
),
_dataset_read_operation("getKnowledgeSpacesByIdDocuments", "knowledge-spaces/{id}/documents"),
_dataset_edit_operation("postKnowledgeSpacesByIdDocuments", "POST", "knowledge-spaces/{id}/documents"),
_dataset_edit_operation(
"deleteKnowledgeSpacesByIdDocumentsBulk",
"DELETE",
"knowledge-spaces/{id}/documents/bulk",
request_headers=("idempotency-key", "x-trace-id"),
),
_dataset_edit_operation(
"postKnowledgeSpacesByIdDocumentsBulk",
"POST",
"knowledge-spaces/{id}/documents/bulk",
),
_dataset_edit_operation(
"postKnowledgeSpacesByIdDocumentsBulkReindex",
"POST",
"knowledge-spaces/{id}/documents/bulk/reindex",
),
_dataset_read_operation(
"getKnowledgeSpacesByIdDocumentsByDocumentId",
"knowledge-spaces/{id}/documents/{documentId}",
),
_dataset_edit_operation(
"deleteKnowledgeSpacesByIdDocumentsByDocumentId",
"DELETE",
"knowledge-spaces/{id}/documents/{documentId}",
request_headers=("idempotency-key", "x-trace-id"),
),
_console_operation(
operation_id="getKnowledgeSpacesByIdLogicalDocuments",
method="GET",
path="knowledge-spaces/{id}/logical-documents",
rbac_permission=RBACPermission.DATASET_READONLY,
legacy_role="reader",
),
_dataset_edit_operation(
"deleteKnowledgeSpacesByIdLogicalDocumentsByDocumentId",
"DELETE",
"knowledge-spaces/{id}/logical-documents/{documentId}",
request_headers=("idempotency-key", "x-trace-id"),
),
_dataset_read_operation(
"getKnowledgeSpacesByIdDocumentsByDocumentIdOutline",
"knowledge-spaces/{id}/documents/{documentId}/outline",
),
_console_operation(
operation_id="getKnowledgeSpacesByIdLogicalDocumentsByDocumentId",
method="GET",
path="knowledge-spaces/{id}/logical-documents/{documentId}",
rbac_permission=RBACPermission.DATASET_READONLY,
legacy_role="reader",
),
_console_operation(
operation_id="getKnowledgeSpacesByIdDocumentsByDocumentIdRevisions",
method="GET",
path="knowledge-spaces/{id}/documents/{documentId}/revisions",
rbac_permission=RBACPermission.DATASET_READONLY,
legacy_role="reader",
),
_dataset_edit_operation(
"postKnowledgeSpacesByIdDocumentsByDocumentIdRevisionsByRevisionRollback",
"POST",
"knowledge-spaces/{id}/documents/{documentId}/revisions/{revision}/rollback",
),
_dataset_edit_operation(
"patchKnowledgeSpacesByIdDocumentsByDocumentIdMetadata",
"PATCH",
"knowledge-spaces/{id}/documents/{documentId}/metadata",
),
_console_operation(
operation_id="getKnowledgeSpacesByIdDocumentsByDocumentIdRevisionsByRevisionChunks",
method="GET",
path="knowledge-spaces/{id}/documents/{documentId}/revisions/{revision}/chunks",
rbac_permission=RBACPermission.DATASET_READONLY,
legacy_role="reader",
),
_dataset_read_operation(
"getKnowledgeSpacesByIdDocumentsByDocumentIdRevisionsByRevisionChunksByChunkId",
"knowledge-spaces/{id}/documents/{documentId}/revisions/{revision}/chunks/{chunkId}",
),
_dataset_edit_operation(
"postKnowledgeSpacesByIdDocumentsByDocumentIdRevisionsByRevisionChunksByChunkIdState",
"POST",
"knowledge-spaces/{id}/documents/{documentId}/revisions/{revision}/chunks/{chunkId}/state",
),
_console_operation(
operation_id="getKnowledgeSpacesByIdProcessingTasks",
method="GET",
path="knowledge-spaces/{id}/processing-tasks",
rbac_permission=RBACPermission.DATASET_READONLY,
legacy_role="reader",
),
_dataset_read_operation(
"getKnowledgeSpacesByIdDocumentsByDocumentIdProcessingTasks",
"knowledge-spaces/{id}/documents/{documentId}/processing-tasks",
),
_dataset_read_operation(
"getKnowledgeSpacesByIdDocumentsByDocumentIdProcessingTasksByTaskId",
"knowledge-spaces/{id}/documents/{documentId}/processing-tasks/{taskId}",
),
_console_operation(
operation_id="getKnowledgeSpacesByIdDocumentsByDocumentIdProcessingTasksByTaskIdEvents",
method="GET",
path="knowledge-spaces/{id}/documents/{documentId}/processing-tasks/{taskId}/events",
rbac_permission=RBACPermission.DATASET_READONLY,
legacy_role="reader",
max_response_bytes=67_108_864,
request_headers=("last-event-id", "x-trace-id"),
response_kind="stream",
response_media_types=("text/event-stream",),
),
_console_operation(
operation_id="deleteKnowledgeSpacesByIdDocumentsByDocumentIdProcessingTasksByTaskId",
method="DELETE",
path="knowledge-spaces/{id}/documents/{documentId}/processing-tasks/{taskId}",
rbac_permission=RBACPermission.DATASET_EDIT,
legacy_role="dataset_editor",
),
_console_operation(
operation_id="postKnowledgeSpacesByIdDocumentsByDocumentIdProcessingTasksByTaskIdRetry",
method="POST",
path="knowledge-spaces/{id}/documents/{documentId}/processing-tasks/{taskId}/retry",
rbac_permission=RBACPermission.DATASET_EDIT,
legacy_role="dataset_editor",
),
_dataset_read_operation(
"getKnowledgeSpacesByIdDocumentsByDocumentIdSettings",
"knowledge-spaces/{id}/documents/{documentId}/settings",
),
_dataset_edit_operation(
"putKnowledgeSpacesByIdDocumentsByDocumentIdSettings",
"PUT",
"knowledge-spaces/{id}/documents/{documentId}/settings",
),
_dataset_read_operation("getJobsById", "jobs/{id}"),
_dataset_edit_operation("deleteJobsById", "DELETE", "jobs/{id}"),
_dataset_edit_operation("postJobsByIdRetry", "POST", "jobs/{id}/retry"),
_dataset_read_operation("getDeletionJobsByJobId", "deletion-jobs/{jobId}"),
_dataset_edit_operation(
"postDeletionJobsByJobIdRetry",
"POST",
"deletion-jobs/{jobId}/retry",
request_headers=("idempotency-key", "x-trace-id"),
),
_dataset_read_operation("getBulkJobsById", "bulk-jobs/{id}"),
)
+118 -68
View File
@@ -1,33 +1,32 @@
"""Transport-only forwarding for the explicitly enabled KnowledgeFS Console operations.
"""Authorize and forward the explicitly enabled KnowledgeFS Console operations.
KnowledgeFS owns the request and response contract. This module binds short-lived
account and workspace identities, enforces Dify's coarse workspace policy, and
normalizes transport failures. Dify deliberately maintains a small product-facing
operation registry instead of exposing the full upstream OpenAPI surface. The
dedicated request path uses Dify's shared SSRF policy, never follows redirects,
bounds buffered responses, and rejects compressed responses.
The dedicated request path uses Dify's shared SSRF policy, never follows redirects,
bounds buffered responses, and rejects compressed streaming responses.
"""
from __future__ import annotations
from collections.abc import Iterable, Mapping
from dataclasses import dataclass
from datetime import UTC, datetime, timedelta
from http import HTTPStatus
from typing import Final, Literal, NamedTuple, Protocol
from typing import NamedTuple, Protocol
import httpx
import jwt
from configs import dify_config
from core.helper import ssrf_proxy
from core.rbac import RBACPermission, RBACResourceScope
from core.rbac import RBACResourceScope
from core.tools.errors import ToolSSRFError
from models import Account
from services.enterprise.rbac_service import RBACService
type KnowledgeFSMethod = Literal["DELETE", "GET", "PATCH", "POST", "PUT"]
type KnowledgeFSResponseKind = Literal["binary", "buffered", "stream"]
type KnowledgeFSRequiredScope = Literal["knowledge-spaces:read", "knowledge-spaces:write"]
from services.knowledge_fs_operations import (
KNOWLEDGE_FS_CONSOLE_OPERATIONS,
KnowledgeFSMethod,
KnowledgeFSOperation,
KnowledgeFSResponseKind,
)
_JWT_AUDIENCE = "knowledge-fs"
_JWT_ISSUER = "dify"
@@ -35,56 +34,55 @@ _JWT_TTL_SECONDS = 60
_MAX_BUFFERED_RESPONSE_BYTES = 1024 * 1024
class KnowledgeFSOperation(NamedTuple):
operation_id: str
method: KnowledgeFSMethod
path: str
response_kind: KnowledgeFSResponseKind
required_scope: KnowledgeFSRequiredScope
rbac_permission: RBACPermission
requires_dataset_editor: bool
max_response_bytes: int
request_headers: tuple[str, ...]
response_headers: tuple[str, ...]
response_media_types: tuple[str, ...]
KNOWLEDGE_FS_CONSOLE_OPERATIONS: Final[tuple[KnowledgeFSOperation, ...]] = (
KnowledgeFSOperation(
operation_id="listKnowledgeSpaces",
method="GET",
path="knowledge-spaces",
response_kind="buffered",
required_scope="knowledge-spaces:read",
rbac_permission=RBACPermission.DATASET_READONLY,
requires_dataset_editor=False,
max_response_bytes=1_048_576,
request_headers=("x-trace-id",),
response_headers=("x-trace-id",),
response_media_types=("application/json",),
),
KnowledgeFSOperation(
operation_id="createKnowledgeSpace",
method="POST",
path="knowledge-spaces",
response_kind="buffered",
required_scope="knowledge-spaces:write",
rbac_permission=RBACPermission.DATASET_CREATE_AND_MANAGEMENT,
requires_dataset_editor=True,
max_response_bytes=1_048_576,
request_headers=("x-trace-id",),
response_headers=("x-trace-id",),
response_media_types=("application/json",),
),
)
class KnowledgeFSUpstreamResponse(NamedTuple):
response: httpx.Response
response_kind: KnowledgeFSResponseKind
operation: KnowledgeFSOperation
_AUTHORIZATION_MARKER = object()
@dataclass(eq=False, frozen=True, init=False, slots=True)
class KnowledgeFSAuthorization:
"""Single-use forwarding capability created after Dify workspace policy checks.
Callers obtain this value from :func:`authorize_knowledge_fs_request`. Direct
construction and repeated forwarding are rejected before outbound I/O.
"""
account_id: str
tenant_id: str
operation: KnowledgeFSOperation
_used: bool
def __init__(
self,
account_id: str,
tenant_id: str,
operation: KnowledgeFSOperation,
*,
_marker: object | None = None,
) -> None:
if _marker is not _AUTHORIZATION_MARKER:
raise KnowledgeFSAccessDeniedError("KnowledgeFS authorization must be created by workspace authorization")
object.__setattr__(self, "account_id", account_id)
object.__setattr__(self, "tenant_id", tenant_id)
object.__setattr__(self, "operation", operation)
object.__setattr__(self, "_used", False)
def consume(self) -> tuple[str, str, KnowledgeFSOperation]:
"""Return the authorized principals and canonical operation exactly once.
Raises:
KnowledgeFSAccessDeniedError: The capability was already consumed.
"""
if self._used:
raise KnowledgeFSAccessDeniedError("KnowledgeFS authorization has already been used")
object.__setattr__(self, "_used", True)
return self.account_id, self.tenant_id, self.operation
class _RequestHeaders(Protocol):
def items(self) -> Iterable[tuple[str, str]]: ...
@@ -113,20 +111,29 @@ def authorize_knowledge_fs_request(
*,
account: Account,
tenant_id: str,
operation: KnowledgeFSOperation,
) -> None:
method: KnowledgeFSMethod,
path: str,
) -> KnowledgeFSAuthorization:
"""Enforce Dify's workspace policy before KFS performs resource authorization.
Args:
account: Authenticated Dify account with its current workspace role.
tenant_id: Current Dify workspace identifier.
operation: Dify-maintained KnowledgeFS operation and policy metadata.
method: Requested upstream HTTP method.
path: Requested relative KnowledgeFS path.
Raises:
KnowledgeFSRouteNotAllowedError: The method and path do not resolve to a declared operation.
KnowledgeFSAccessDeniedError: The account lacks a required legacy or enterprise permission.
Returns:
A request-scoped capability binding the authorized account, workspace, and operation.
"""
if operation.requires_dataset_editor and not account.is_dataset_editor:
raise KnowledgeFSAccessDeniedError("KnowledgeFS mutations require dataset edit access")
operation = get_knowledge_fs_operation(method, path)
if operation.legacy_role == "dataset_editor" and not account.is_dataset_editor:
raise KnowledgeFSAccessDeniedError("KnowledgeFS operation requires dataset edit access")
if operation.legacy_role == "admin" and not account.is_admin_or_owner:
raise KnowledgeFSAccessDeniedError("KnowledgeFS operation requires workspace administration access")
if not RBACService.CheckAccess.check(
tenant_id,
account.id,
@@ -134,6 +141,7 @@ def authorize_knowledge_fs_request(
resource_type=RBACResourceScope.DATASET.value,
):
raise KnowledgeFSAccessDeniedError("KnowledgeFS operation is denied by workspace RBAC")
return KnowledgeFSAuthorization(account.id, tenant_id, operation, _marker=_AUTHORIZATION_MARKER)
def proxy_knowledge_fs_request(
@@ -149,20 +157,62 @@ def proxy_knowledge_fs_request(
request_headers: _RequestHeaders | None = None,
) -> KnowledgeFSUpstreamResponse:
"""Authorize and forward one allowlisted KnowledgeFS request as a single use case."""
operation = get_knowledge_fs_operation(method, path)
authorize_knowledge_fs_request(
authorization = authorize_knowledge_fs_request(
account=account,
tenant_id=tenant_id,
operation=operation,
method=method,
path=path,
)
return proxy_authorized_knowledge_fs_request(
authorization=authorization,
accept=accept,
content_type=content_type,
query=query,
body=body,
request_headers=request_headers,
)
def proxy_authorized_knowledge_fs_request(
*,
authorization: KnowledgeFSAuthorization,
accept: str | None = None,
content_type: str | None = None,
query: bytes | None = None,
body: bytes | None = None,
request_headers: _RequestHeaders | None = None,
) -> KnowledgeFSUpstreamResponse:
"""Forward one request whose operation and workspace policy were already authorized.
This performs one outbound KnowledgeFS request and does not repeat Dify RBAC checks.
Args:
authorization: Request-scoped capability returned by :func:`authorize_knowledge_fs_request`.
accept: Original Accept header, when present.
content_type: Original request Content-Type header, when present.
query: Original encoded query string from the Console request.
body: Original request body, when present.
request_headers: Incoming headers; only names declared by the operation are forwarded.
Returns:
The bounded KnowledgeFS response together with its transport metadata.
Raises:
KnowledgeFSConfigurationError: The connection is incomplete or blocked by outbound policy.
KnowledgeFSRouteNotAllowedError: A forwarded request header is outside the operation contract.
KnowledgeFSTimeoutError: KnowledgeFS exceeds the configured timeout.
KnowledgeFSTransportError: The request fails or its response violates transport bounds.
"""
account_id, tenant_id, operation = authorization.consume()
incoming_request_headers = {name.lower(): value for name, value in (request_headers or {}).items()}
contract_request_headers = {
name: incoming_request_headers[name] for name in operation.request_headers if name in incoming_request_headers
}
return _forward_knowledge_fs_request(
account_id=account.id,
method=method,
path=path,
account_id=account_id,
method=operation.method,
path=operation.path,
tenant_id=tenant_id,
accept=accept,
content_type=content_type,
+12 -1
View File
@@ -13,6 +13,7 @@ from core.tools.utils.web_reader_tool import get_image_upload_file_ids
from extensions.ext_storage import storage
from models.dataset import Dataset, DatasetMetadataBinding, DocumentSegment
from models.model import UploadFile
from tasks.refresh_billing_vector_space_task import schedule_billing_vector_space_refresh
logger = logging.getLogger(__name__)
@@ -21,7 +22,12 @@ BATCH_SIZE = 1000
@shared_task(queue="dataset")
def batch_clean_document_task(document_ids: list[str], dataset_id: str, doc_form: str | None, file_ids: list[str]):
def batch_clean_document_task(
document_ids: list[str],
dataset_id: str,
doc_form: str | None,
file_ids: list[str],
) -> None:
"""
Clean document when document deleted.
:param document_ids: document ids
@@ -40,6 +46,7 @@ def batch_clean_document_task(document_ids: list[str], dataset_id: str, doc_form
index_node_ids: list[str] = []
segment_ids: list[str] = []
total_image_upload_file_ids: list[str] = []
dataset_tenant_id: str | None = None
try:
# ============ Step 1: Query segment and file data (short read-only transaction) ============
@@ -88,6 +95,7 @@ def batch_clean_document_task(document_ids: list[str], dataset_id: str, doc_form
delete_summaries=True,
session=session,
)
dataset_tenant_id = dataset.tenant_id
except Exception:
logger.exception(
"Failed to clean vector index for dataset_id: %s, document_ids: %s, index_node_ids count: %d",
@@ -203,6 +211,9 @@ def batch_clean_document_task(document_ids: list[str], dataset_id: str, doc_form
dataset_id,
)
if dataset_tenant_id is not None:
schedule_billing_vector_space_refresh(dataset_tenant_id)
end_at = time.perf_counter()
logger.info(
click.style(
+5
View File
@@ -24,6 +24,7 @@ from models.dataset import (
)
from models.model import UploadFile
from models.workflow import Workflow
from tasks.refresh_billing_vector_space_task import schedule_billing_vector_space_refresh
logger = logging.getLogger(__name__)
@@ -52,6 +53,7 @@ def clean_dataset_task(
"""
logger.info(click.style(f"Start clean dataset when dataset deleted: {dataset_id}", fg="green"))
start_at = time.perf_counter()
vector_cleanup_succeeded = False
with session_factory.create_session() as session:
try:
@@ -93,6 +95,7 @@ def clean_dataset_task(
try:
index_processor = IndexProcessorFactory(doc_form).init_index_processor()
index_processor.clean(dataset, None, with_keywords=True, delete_child_chunks=True, session=session)
vector_cleanup_succeeded = True
logger.info(click.style(f"Successfully cleaned vector database for dataset: {dataset_id}", fg="green"))
except Exception:
logger.exception(click.style(f"Failed to clean vector database for dataset {dataset_id}", fg="red"))
@@ -186,6 +189,8 @@ def clean_dataset_task(
session.execute(file_delete_stmt)
session.commit()
if vector_cleanup_succeeded:
schedule_billing_vector_space_refresh(dataset.tenant_id)
end_at = time.perf_counter()
logger.info(
click.style(
+13 -1
View File
@@ -11,12 +11,18 @@ from core.tools.utils.web_reader_tool import get_image_upload_file_ids
from extensions.ext_storage import storage
from models.dataset import Dataset, DatasetMetadataBinding, DocumentSegment, SegmentAttachmentBinding
from models.model import UploadFile
from tasks.refresh_billing_vector_space_task import schedule_billing_vector_space_refresh
logger = logging.getLogger(__name__)
@shared_task(queue="dataset")
def clean_document_task(document_id: str, dataset_id: str, doc_form: str, file_id: str | None):
def clean_document_task(
document_id: str,
dataset_id: str,
doc_form: str,
file_id: str | None,
) -> None:
"""
Clean document when document deleted.
:param document_id: document id
@@ -29,6 +35,7 @@ def clean_document_task(document_id: str, dataset_id: str, doc_form: str, file_i
logger.info(click.style(f"Start clean document when document deleted: {document_id}", fg="green"))
start_at = time.perf_counter()
total_attachment_files = []
vector_cleanup_succeeded = False
with session_factory.create_session() as session:
try:
@@ -37,6 +44,7 @@ def clean_document_task(document_id: str, dataset_id: str, doc_form: str, file_i
if not dataset:
raise Exception("Document has no dataset")
dataset_tenant_id = dataset.tenant_id
segments = session.scalars(select(DocumentSegment).where(DocumentSegment.document_id == document_id)).all()
# Use JOIN to fetch attachments with bindings in a single query
attachments_with_bindings = session.execute(
@@ -82,6 +90,7 @@ def clean_document_task(document_id: str, dataset_id: str, doc_form: str, file_i
delete_summaries=True,
session=session,
)
vector_cleanup_succeeded = True
except Exception:
logger.exception(
"Failed to clean vector / keyword index in clean_document_task, "
@@ -154,6 +163,9 @@ def clean_document_task(document_id: str, dataset_id: str, doc_form: str, file_i
)
)
if vector_cleanup_succeeded:
schedule_billing_vector_space_refresh(dataset_tenant_id)
end_at = time.perf_counter()
logger.info(
click.style(
@@ -0,0 +1,59 @@
import logging
from celery import shared_task
from opentelemetry import metrics
from configs import dify_config
from services.billing_service import BillingService
logger = logging.getLogger(__name__)
_MAX_RETRIES = 3
_RETRY_DELAY_SECONDS = 30
_refresh_counter = metrics.get_meter(__name__).create_counter(
"billing.vector_space_cache_refresh.count",
description="Number of billing vector-space cache refresh outcomes",
)
@shared_task(queue="dataset", bind=True, max_retries=_MAX_RETRIES, default_retry_delay=_RETRY_DELAY_SECONDS)
def refresh_billing_vector_space_task(self, tenant_id: str) -> None:
"""Refresh billing vector-space usage after vector cleanup has completed."""
if not dify_config.BILLING_ENABLED:
return
try:
BillingService.invalidate_vector_space_cache(tenant_id)
except Exception as exc:
if self.request.retries >= _MAX_RETRIES:
_refresh_counter.add(1, {"outcome": "exhausted"})
logger.exception(
"Billing vector-space cache refresh retry budget exhausted, tenant_id=%s",
tenant_id,
)
raise
_refresh_counter.add(1, {"outcome": "retry"})
logger.warning(
"Billing vector-space cache refresh failed, scheduling retry %d/%d, tenant_id=%s",
self.request.retries + 1,
_MAX_RETRIES,
tenant_id,
exc_info=True,
)
raise self.retry(exc=exc, countdown=_RETRY_DELAY_SECONDS * (2**self.request.retries))
_refresh_counter.add(1, {"outcome": "success"})
logger.info("Billing vector-space cache refreshed, tenant_id=%s", tenant_id)
def schedule_billing_vector_space_refresh(tenant_id: str) -> None:
"""Dispatch a best-effort billing refresh without changing cleanup status."""
if not dify_config.BILLING_ENABLED:
return
try:
refresh_billing_vector_space_task.delay(tenant_id)
except Exception:
_refresh_counter.add(1, {"outcome": "dispatch_failure"})
logger.exception("Failed to dispatch billing vector-space cache refresh, tenant_id=%s", tenant_id)
@@ -318,6 +318,7 @@ def test_oauth_account_successful_retrieval(
assert response.status_code == 200
assert response.get_json() == {
"id": account.id,
"name": "Test User",
"email": account.email,
"avatar": "avatar_url",
@@ -9,7 +9,9 @@ from flask import Flask
from sqlalchemy.orm import Session
from werkzeug.exceptions import Forbidden
from configs import dify_config
from controllers.web.site import AppSiteApi, WebAppSiteResponse, WebModelConfigResponse
from extensions.storage.storage_type import StorageType
from models import Tenant, TenantStatus
from models.account import TenantCustomConfigDict
from models.model import App, AppMode, AppModelConfig, CustomizeTokenStrategy, EndUser, Site
@@ -96,6 +98,39 @@ class TestAppSiteApi:
assert result["plan"] == "basic"
assert result["enable_site"] is True
@patch("controllers.web.site.FileService.get_file_presigned_url")
@patch("controllers.web.site.FeatureService.get_features")
def test_image_icon_uses_s3_presigned_url(
self,
mock_features: MagicMock,
mock_get_file_presigned_url: MagicMock,
app: Flask,
db_session_with_containers: Session,
) -> None:
app.config["RESTX_MASK_HEADER"] = "X-Fields"
tenant = _create_tenant(db_session_with_containers)
app_model = _create_app(db_session_with_containers, tenant.id)
site = _create_site(db_session_with_containers, app_model.id)
site.icon_type = "image"
site.icon = "11111111-1111-4111-8111-111111111111"
db_session_with_containers.commit()
end_user = _end_user(tenant.id, app_model.id)
mock_features.return_value = FeatureModel(can_replace_logo=False)
mock_get_file_presigned_url.return_value = "https://s3.example.com/icon.png?signature=test"
with (
patch.object(dify_config, "EDITION", "CLOUD"),
patch.object(dify_config, "STORAGE_TYPE", StorageType.S3),
app.test_request_context("/site"),
):
result = AppSiteApi().get(app_model, end_user)
assert result["site"]["icon_url"] == "https://s3.example.com/icon.png?signature=test"
mock_get_file_presigned_url.assert_called_once_with(
file_id="11111111-1111-4111-8111-111111111111",
tenant_id=tenant.id,
)
def test_missing_site_raises_forbidden(self, app: Flask, db_session_with_containers: Session) -> None:
app.config["RESTX_MASK_HEADER"] = "X-Fields"
tenant = _create_tenant(db_session_with_containers)
@@ -212,6 +212,17 @@ def test_generate_specs_include_console_contract_shapes_for_schema_migration(tmp
assert {"type": "null"} in app_detail_nullable_schema["anyOf"]
assert schemas["RecommendedAppInfoResponse"]["properties"]["icon_url"]["readOnly"] is True
assert schemas["InstalledAppInfoResponse"]["properties"]["icon_url"]["readOnly"] is True
assert _response_schema(paths["/apps/{app_id}"]["get"])["$ref"] == "#/components/schemas/AppDetailWithSite"
app_model_config = schemas["AppDetailWithSite"]["properties"]["model_config"]
assert {"$ref": "#/components/schemas/AppModelConfigResponse"} in app_model_config["anyOf"]
app_detail = schemas["AppDetail"]
assert "mode" in app_detail["properties"]
assert "mode_compatible_with_agent" not in app_detail["properties"]
sync_draft_workflow = schemas["SyncDraftWorkflowResponse"]
assert _response_schema(paths["/apps/{app_id}/workflows/draft"]["post"])["$ref"] == (
"#/components/schemas/SyncDraftWorkflowResponse"
)
assert sync_draft_workflow["properties"]["updated_at"]["type"] == "integer"
tool_icon_schema = schemas["ExploreAppMetaResponse"]["properties"]["tool_icons"]["additionalProperties"]
assert {"type": "string"} in tool_icon_schema["anyOf"]
assert {"additionalProperties": True, "type": "object"} in tool_icon_schema["anyOf"]
@@ -1,15 +1,24 @@
"""Unit tests for the reset-encrypt-key-pair CLI command (#35396).
"""SQLite-backed tests for the reset-encrypt-key-pair CLI command (#35396).
The command must purge every table that stores ciphertext encrypted with the
tenant's asymmetric key, otherwise stale rows cause downstream API failures
such as `/console/api/workspaces/current/tool-providers` returning 500.
Tests bind the command-owned transaction to the fixture engine and assert the
committed state rather than inspecting fabricated ``Session.execute`` calls.
"""
from unittest.mock import MagicMock, patch
from types import SimpleNamespace
import pytest
from sqlalchemy import select
from sqlalchemy.orm import Session
import commands
from commands import system as system_commands
from models.provider import Provider, ProviderModel
from core.tools.entities.tool_entities import ApiProviderSchemaType
from graphon.model_runtime.entities.model_entities import ModelType
from models import Tenant
from models.provider import Provider, ProviderModel, ProviderType
from models.tools import ApiToolProvider, BuiltinToolProvider, MCPToolProvider
@@ -21,17 +30,60 @@ def _invoke_reset() -> int:
return 0
def _delete_targets(session_mock: MagicMock) -> list:
"""Extract the model class targeted by each `delete(...)` call on the session."""
targets = []
for call in session_mock.execute.call_args_list:
stmt = call.args[0]
# `delete(Foo)` constructs a `Delete` statement whose entity is `Foo`.
try:
targets.append(stmt.table.name)
except AttributeError:
targets.append(repr(stmt))
return targets
TENANT_ID = "11111111-1111-1111-1111-111111111111"
OTHER_TENANT_ID = "11111111-1111-1111-1111-111111111112"
USER_ID = "22222222-2222-2222-2222-222222222222"
def _tenant(tenant_id: str, *, name: str = "Test tenant") -> Tenant:
tenant = Tenant(name=name, encrypt_public_key="old-key")
tenant.id = tenant_id
return tenant
def _encrypted_rows(tenant_id: str, *, suffix: str = "1") -> tuple[object, ...]:
"""Build one persisted credential-bearing row for every purge target."""
return (
Provider(tenant_id=tenant_id, provider_name=f"provider-{suffix}"),
ProviderModel(
tenant_id=tenant_id,
provider_name=f"provider-{suffix}",
model_name=f"model-{suffix}",
model_type=ModelType.LLM,
),
BuiltinToolProvider(
name=f"builtin-credential-{suffix}",
tenant_id=tenant_id,
user_id=USER_ID,
provider=f"builtin-{suffix}",
encrypted_credentials="ciphertext",
),
ApiToolProvider(
name=f"api-{suffix}",
icon="icon",
schema="{}",
schema_type_str=ApiProviderSchemaType.OPENAPI,
user_id=USER_ID,
tenant_id=tenant_id,
description="description",
tools_str="[]",
credentials_str="{}",
),
MCPToolProvider(
name=f"mcp-{suffix}",
server_identifier=f"server-{suffix}",
server_url="ciphertext",
server_url_hash=f"hash-{suffix}",
icon=None,
tenant_id=tenant_id,
user_id=USER_ID,
encrypted_credentials="ciphertext",
),
)
def _bind_command_to_sqlite(monkeypatch: pytest.MonkeyPatch, session: Session) -> None:
monkeypatch.setattr(system_commands, "db", SimpleNamespace(engine=session.get_bind()))
def test_reset_aborts_when_not_self_hosted(monkeypatch, capsys):
@@ -44,65 +96,73 @@ def test_reset_aborts_when_not_self_hosted(monkeypatch, capsys):
assert "only for SELF_HOSTED" in captured.out
def test_reset_purges_provider_and_tool_tables_for_each_tenant(monkeypatch, capsys):
@pytest.mark.parametrize(
"sqlite_session",
[(Tenant, Provider, ProviderModel, BuiltinToolProvider, ApiToolProvider, MCPToolProvider)],
indirect=True,
)
def test_reset_purges_provider_and_tool_tables_for_each_tenant(
monkeypatch: pytest.MonkeyPatch, capsys: pytest.CaptureFixture[str], sqlite_session: Session
) -> None:
"""The command must purge LLM provider rows AND every tool provider table
that stores ciphertext encrypted under the tenant key (#35396)."""
monkeypatch.setattr(system_commands.dify_config, "EDITION", "SELF_HOSTED")
monkeypatch.setattr(system_commands, "generate_key_pair", lambda tenant_id: f"new-key-{tenant_id}")
_bind_command_to_sqlite(monkeypatch, sqlite_session)
fake_tenant = MagicMock(id="tenant-abc", encrypt_public_key="old-key")
session = MagicMock()
session.scalars.return_value.all.return_value = [fake_tenant]
tenant = _tenant(TENANT_ID)
other_tenant = _tenant(OTHER_TENANT_ID, name="Other tenant")
system_provider = Provider(
tenant_id=TENANT_ID,
provider_name="system-provider",
provider_type=ProviderType.SYSTEM,
)
sqlite_session.add_all((tenant, other_tenant, system_provider, *_encrypted_rows(TENANT_ID)))
sqlite_session.commit()
fake_sessionmaker = MagicMock()
fake_sessionmaker.begin.return_value.__enter__.return_value = session
fake_sessionmaker.begin.return_value.__exit__.return_value = False
with (
patch.object(system_commands, "db", MagicMock()),
patch.object(system_commands, "sessionmaker", return_value=fake_sessionmaker),
):
exit_code = _invoke_reset()
exit_code = _invoke_reset()
captured = capsys.readouterr()
assert exit_code == 0
assert "tenant-abc" in captured.out
assert TENANT_ID in captured.out
# New key pair generated and assigned.
assert fake_tenant.encrypt_public_key == "new-key-tenant-abc"
# Every encrypted-credential table should have been purged for this tenant.
table_names = _delete_targets(session)
expected = {
Provider.__tablename__,
ProviderModel.__tablename__,
BuiltinToolProvider.__tablename__,
ApiToolProvider.__tablename__,
MCPToolProvider.__tablename__,
}
assert expected.issubset(set(table_names)), f"missing purges: expected {expected}, got {table_names}"
sqlite_session.expire_all()
assert sqlite_session.get(Tenant, TENANT_ID).encrypt_public_key == f"new-key-{TENANT_ID}"
assert sqlite_session.get(Tenant, OTHER_TENANT_ID).encrypt_public_key == f"new-key-{OTHER_TENANT_ID}"
assert sqlite_session.scalars(select(Provider).where(Provider.provider_type == ProviderType.CUSTOM)).all() == []
assert sqlite_session.scalars(select(ProviderModel)).all() == []
assert sqlite_session.scalars(select(BuiltinToolProvider)).all() == []
assert sqlite_session.scalars(select(ApiToolProvider)).all() == []
assert sqlite_session.scalars(select(MCPToolProvider)).all() == []
assert (
sqlite_session.scalar(select(Provider).where(Provider.provider_type == ProviderType.SYSTEM)) is system_provider
)
def test_reset_iterates_all_tenants(monkeypatch, capsys):
@pytest.mark.parametrize(
"sqlite_session",
[(Tenant, Provider, ProviderModel, BuiltinToolProvider, ApiToolProvider, MCPToolProvider)],
indirect=True,
)
def test_reset_iterates_all_tenants(monkeypatch: pytest.MonkeyPatch, sqlite_session: Session) -> None:
"""Multi-tenant deployments must purge every tenant, not just the first."""
monkeypatch.setattr(system_commands.dify_config, "EDITION", "SELF_HOSTED")
monkeypatch.setattr(system_commands, "generate_key_pair", lambda tenant_id: f"new-key-{tenant_id}")
tenants = [MagicMock(id=f"tenant-{i}", encrypt_public_key="old") for i in range(3)]
session = MagicMock()
session.scalars.return_value.all.return_value = tenants
_bind_command_to_sqlite(monkeypatch, sqlite_session)
tenant_ids = [f"11111111-1111-1111-1111-{index:012d}" for index in range(3)]
tenants = [_tenant(tenant_id, name=f"Tenant {index}") for index, tenant_id in enumerate(tenant_ids)]
for index, tenant in enumerate(tenants):
sqlite_session.add(tenant)
sqlite_session.add_all(_encrypted_rows(tenant.id, suffix=str(index)))
sqlite_session.commit()
fake_sessionmaker = MagicMock()
fake_sessionmaker.begin.return_value.__enter__.return_value = session
fake_sessionmaker.begin.return_value.__exit__.return_value = False
assert _invoke_reset() == 0
with (
patch.object(system_commands, "db", MagicMock()),
patch.object(system_commands, "sessionmaker", return_value=fake_sessionmaker),
):
_invoke_reset()
# Five purges per tenant × 3 tenants = 15 execute calls.
assert session.execute.call_count == 15
for tenant in tenants:
assert tenant.encrypt_public_key == f"new-key-{tenant.id}"
sqlite_session.expire_all()
persisted_tenants = sqlite_session.scalars(select(Tenant).order_by(Tenant.id)).all()
assert [tenant.encrypt_public_key for tenant in persisted_tenants] == [
f"new-key-{tenant_id}" for tenant_id in tenant_ids
]
for model in (Provider, ProviderModel, BuiltinToolProvider, ApiToolProvider, MCPToolProvider):
assert sqlite_session.scalars(select(model)).all() == []
+38 -24
View File
@@ -37,6 +37,7 @@ os.environ.setdefault("STORAGE_TYPE", "opendal")
from core.db.session_factory import configure_session_factory, session_factory
from extensions import ext_redis
from models.account import Account, Tenant, TenantAccountJoin, TenantAccountRole
from models.base import TypeBase
@@ -148,32 +149,45 @@ def _configure_session_factory(_unit_test_engine):
configure_session_factory(_unit_test_engine, expire_on_commit=False)
def setup_mock_tenant_owner_execute_result(mock_db, mock_tenant, mock_owner):
"""
Helper to stub the tenant-owner execute result for service API app authentication.
def persist_service_api_tenant_owner(session: Session, tenant: Tenant, owner: Account) -> TenantAccountJoin:
"""Persist the owner identity resolved by service-API app authentication.
The validate_app_token decorator currently resolves the active tenant owner
via db.session.execute(select(Tenant, Account)...).one_or_none().
Args:
mock_db: The mocked db object
mock_tenant: Mock tenant object to return
mock_owner: Mock owner object to return from the execute result
The legacy name is retained temporarily for consumers on independent
conversion branches, but this helper no longer fabricates an execute result.
"""
membership = TenantAccountJoin(
tenant_id=tenant.id,
account_id=owner.id,
role=TenantAccountRole.OWNER,
)
owner._current_tenant = tenant
session.add_all([tenant, owner, membership])
session.commit()
return membership
def persist_service_api_dataset_owner(
session: Session,
tenant: Tenant,
tenant_account_join: TenantAccountJoin,
) -> None:
"""Persist the tenant-owner mapping resolved by dataset-token authentication."""
session.add_all([tenant, tenant_account_join])
session.commit()
def setup_mock_tenant_owner_execute_result(mock_db: MagicMock, mock_tenant: object, mock_owner: object) -> None:
"""Stub the legacy owner query; SQLite-backed tests use ``persist_service_api_tenant_owner``."""
mock_db.session.execute.return_value.one_or_none.return_value = (mock_tenant, mock_owner)
def setup_mock_dataset_owner_execute_result(mock_db, mock_tenant, mock_tenant_account_join):
"""
Helper to stub the tenant-owner execute result for dataset token authentication.
The validate_dataset_token decorator currently resolves the owner mapping via
db.session.execute(select(Tenant, TenantAccountJoin)...).one_or_none(), and
then loads the Account separately via db.session.get(...).
Args:
mock_db: The mocked db object
mock_tenant: Mock tenant object to return
mock_tenant_account_join: Mock tenant-account join object to return
"""
mock_db.session.execute.return_value.one_or_none.return_value = (mock_tenant, mock_tenant_account_join)
def setup_mock_dataset_owner_execute_result(
mock_db: MagicMock,
mock_tenant: object,
mock_tenant_account_join: object,
) -> None:
"""Stub the legacy dataset-owner query; SQLite tests use ``persist_service_api_dataset_owner``."""
mock_db.session.execute.return_value.one_or_none.return_value = (
mock_tenant,
mock_tenant_account_join,
)
@@ -53,6 +53,7 @@ from controllers.console.app.message import (
AgentMessageFeedbackApi,
AgentMessageSuggestedQuestionApi,
)
from models.agent import AgentConfigDraftType
from services.entities.agent_entities import ComposerSaveStrategy, ComposerVariant
@@ -68,6 +69,20 @@ def _version_response(version_id: str = "version-1") -> dict:
}
def test_query_values_accepts_repeated_and_indexed_arrays() -> None:
app = Flask(__name__)
with app.test_request_context("/?sources=webapp:app-1&sources%5B1%5D=workflow:app-2&sources%5B0%5D=workflow:app-1"):
assert roster_controller._query_values("sources", "source") == [
"webapp:app-1",
"workflow:app-1",
"workflow:app-2",
]
with app.test_request_context("/?source%5B0%5D=workflow:app-3"):
assert roster_controller._query_values("sources", "source") == ["workflow:app-3"]
def _workflow_composer_response(**overrides) -> dict:
response = {
"variant": "workflow",
@@ -371,6 +386,7 @@ def test_agent_app_list_and_create_use_agent_route(
"tenant_id": "tenant-1",
"agent_id": "agent-created",
"account_id": account_id,
"draft_type": AgentConfigDraftType.DEBUG_BUILD,
"commit": False,
}
@@ -544,8 +560,19 @@ def test_agent_app_copy_uses_agent_id_and_returns_agent_detail(
}
def test_agent_debug_conversation_refresh_uses_current_user(
app: Flask, monkeypatch: pytest.MonkeyPatch, account_id: str
@pytest.mark.parametrize(
("payload", "expected_draft_type"),
[
(None, AgentConfigDraftType.DEBUG_BUILD),
({"draft_type": "draft"}, AgentConfigDraftType.DRAFT),
],
)
def test_agent_debug_conversation_refresh_uses_current_user_and_draft_type(
app: Flask,
monkeypatch: pytest.MonkeyPatch,
account_id: str,
payload: dict[str, str] | None,
expected_draft_type: AgentConfigDraftType,
) -> None:
agent_id = "00000000-0000-0000-0000-000000000001"
captured: dict[str, object] = {}
@@ -557,7 +584,9 @@ def test_agent_debug_conversation_refresh_uses_current_user(
monkeypatch.setattr(roster_controller, "_agent_roster_service", lambda *_args: FakeRosterService())
with app.test_request_context(
"/console/api/agent/00000000-0000-0000-0000-000000000001/debug-conversation/refresh", method="POST"
"/console/api/agent/00000000-0000-0000-0000-000000000001/debug-conversation/refresh",
method="POST",
json=payload,
):
response = unwrap(AgentDebugConversationRefreshApi.post)(
AgentDebugConversationRefreshApi(), MagicMock(), "tenant-1", SimpleNamespace(id=account_id), agent_id
@@ -567,7 +596,12 @@ def test_agent_debug_conversation_refresh_uses_current_user(
"debug_conversation_has_messages": False,
"debug_conversation_message_count": 0,
}
assert captured == {"tenant_id": "tenant-1", "agent_id": agent_id, "account_id": account_id}
assert captured == {
"tenant_id": "tenant-1",
"agent_id": agent_id,
"account_id": account_id,
"draft_type": expected_draft_type,
}
def test_agent_publish_and_build_draft_routes_call_composer_service(
@@ -1456,6 +1490,7 @@ def test_build_chat_finalization_helper_forces_debug_build_and_push_prompt(
"current_user": SimpleNamespace(id=account_id),
"app_model": app_model,
"agent_id": "agent-1",
"draft_type": AgentConfigDraftType.DEBUG_BUILD,
}
generate_call = cast(dict[str, object], captured["generate"])
assert generate_call["app_model"] is app_model
@@ -1509,8 +1544,35 @@ def test_drain_streaming_generate_response_raises_when_stream_ends_early() -> No
completion_controller._drain_streaming_generate_response(response)
def test_agent_chat_helper_forces_agent_streaming_and_external_trace(
app: Flask, monkeypatch: pytest.MonkeyPatch, account_id: str
@pytest.mark.parametrize(
("payload_extra", "expected_draft_type", "expected_start_new"),
[
({}, AgentConfigDraftType.DRAFT, True),
({"conversation_id": None}, AgentConfigDraftType.DRAFT, True),
({"conversation_id": ""}, AgentConfigDraftType.DRAFT, True),
(
{"conversation_id": "00000000-0000-0000-0000-000000000001"},
AgentConfigDraftType.DRAFT,
False,
),
({"draft_type": "debug_build"}, AgentConfigDraftType.DEBUG_BUILD, False),
(
{
"draft_type": "debug_build",
"conversation_id": "00000000-0000-0000-0000-000000000001",
},
AgentConfigDraftType.DEBUG_BUILD,
False,
),
],
)
def test_agent_chat_helper_resolves_scoped_conversation_and_forces_streaming(
app: Flask,
monkeypatch: pytest.MonkeyPatch,
account_id: str,
payload_extra: dict[str, str | None],
expected_draft_type: AgentConfigDraftType,
expected_start_new: bool,
) -> None:
app_model = SimpleNamespace(id="app-1", tenant_id="tenant-1", mode="agent")
current_user = SimpleNamespace(id=account_id)
@@ -1520,17 +1582,22 @@ def test_agent_chat_helper_forces_agent_streaming_and_external_trace(
captured.update(kwargs)
return {"answer": "ok"}
def resolve_debug_conversation(**kwargs: object) -> str:
captured["resolve_debug_conversation"] = kwargs
return "00000000-0000-0000-0000-000000000001"
monkeypatch.setattr(completion_controller.AppGenerateService, "generate", generate)
monkeypatch.setattr(
completion_controller,
"_resolve_current_user_agent_debug_conversation_id",
lambda **kwargs: "debug-conversation-1",
resolve_debug_conversation,
)
monkeypatch.setattr(
completion_controller.helper, "compact_generate_response", lambda response: {"response": response}
)
with app.test_request_context(
json={"inputs": {}, "query": "hello", "response_mode": "streaming"}, headers={"X-Trace-Id": "trace-1"}
json={"inputs": {}, "query": "hello", "response_mode": "streaming", **payload_extra},
headers={"X-Trace-Id": "trace-1"},
):
result = completion_controller._create_chat_message(
current_user=current_user, app_model=app_model, session=Mock()
@@ -1541,9 +1608,12 @@ def test_agent_chat_helper_forces_agent_streaming_and_external_trace(
assert captured["streaming"] is True
args = cast(dict[str, object], captured["args"])
assert args["response_mode"] == "streaming"
assert args["conversation_id"] == "debug-conversation-1"
assert args["conversation_id"] == "00000000-0000-0000-0000-000000000001"
assert args["auto_generate_name"] is False
assert args["external_trace_id"] == "trace-1"
resolve_call = cast(dict[str, object], captured["resolve_debug_conversation"])
assert resolve_call["draft_type"] == expected_draft_type
assert resolve_call["start_new"] is expected_start_new
def test_agent_chat_helper_ignores_private_exit_intent_payload_key(
@@ -1591,14 +1661,28 @@ def test_agent_chat_helper_ignores_private_exit_intent_payload_key(
assert completion_controller.AGENT_RUNTIME_EXIT_INTENT_ARG not in args
def test_agent_chat_helper_rejects_foreign_debug_conversation(
app: Flask, monkeypatch: pytest.MonkeyPatch, account_id: str
@pytest.mark.parametrize(
("payload_extra", "expected_draft_type"),
[
({}, AgentConfigDraftType.DRAFT),
({"draft_type": "debug_build"}, AgentConfigDraftType.DEBUG_BUILD),
],
)
def test_agent_chat_helper_rejects_foreign_debug_conversation_before_generation(
app: Flask,
monkeypatch: pytest.MonkeyPatch,
account_id: str,
payload_extra: dict[str, str],
expected_draft_type: AgentConfigDraftType,
) -> None:
app_model = SimpleNamespace(id="app-1", tenant_id="tenant-1", mode="agent")
generate = MagicMock()
resolve_debug_conversation = MagicMock(return_value="owned-conversation")
monkeypatch.setattr(completion_controller.AppGenerateService, "generate", generate)
monkeypatch.setattr(
completion_controller,
"_resolve_current_user_agent_debug_conversation_id",
lambda **kwargs: "owned-conversation",
resolve_debug_conversation,
)
with app.test_request_context(
json={
@@ -1606,6 +1690,7 @@ def test_agent_chat_helper_rejects_foreign_debug_conversation(
"query": "hello",
"response_mode": "streaming",
"conversation_id": "00000000-0000-0000-0000-000000000001",
**payload_extra,
}
):
with pytest.raises(NotFound):
@@ -1617,6 +1702,12 @@ def test_agent_chat_helper_rejects_foreign_debug_conversation(
session=Mock(),
)
resolve_debug_conversation.assert_called_once()
resolve_call = resolve_debug_conversation.call_args.kwargs
assert resolve_call["draft_type"] == expected_draft_type
assert resolve_call["start_new"] is False
generate.assert_not_called()
def test_resolve_current_user_agent_debug_conversation_uses_agent_or_backing_app(
monkeypatch: pytest.MonkeyPatch,
@@ -1631,6 +1722,10 @@ def test_resolve_current_user_agent_debug_conversation_uses_agent_or_backing_app
calls.append({"get_or_create": kwargs})
return f"debug-{kwargs['agent_id']}"
def refresh_agent_app_debug_conversation_id(self, **kwargs: object) -> str:
calls.append({"refresh": kwargs})
return f"new-{kwargs['agent_id']}"
def get_app_backing_agent(self, **kwargs: object) -> object:
calls.append({"get_app_backing_agent": kwargs})
return SimpleNamespace(id="backing-agent")
@@ -1642,6 +1737,8 @@ def test_resolve_current_user_agent_debug_conversation_uses_agent_or_backing_app
current_user=SimpleNamespace(id="account-1"),
app_model=SimpleNamespace(id="app-1"),
agent_id="agent-1",
draft_type=AgentConfigDraftType.DRAFT,
start_new=True,
)
fallback_id = completion_controller._resolve_current_user_agent_debug_conversation_id(
session="session-1", # type: ignore[arg-type]
@@ -1649,13 +1746,45 @@ def test_resolve_current_user_agent_debug_conversation_uses_agent_or_backing_app
current_user=SimpleNamespace(id="account-1"),
app_model=SimpleNamespace(id="app-1"),
agent_id=None,
draft_type=AgentConfigDraftType.DEBUG_BUILD,
)
assert explicit_id == "debug-agent-1"
fallback_preview_id = completion_controller._resolve_current_user_agent_debug_conversation_id(
session="session-1", # type: ignore[arg-type]
current_tenant_id="tenant-1",
current_user=SimpleNamespace(id="account-1"),
app_model=SimpleNamespace(id="app-1"),
agent_id=None,
draft_type=AgentConfigDraftType.DRAFT,
start_new=True,
)
assert explicit_id == "new-agent-1"
assert fallback_id == "debug-backing-agent"
assert calls[1] == {"get_or_create": {"tenant_id": "tenant-1", "agent_id": "agent-1", "account_id": "account-1"}}
assert fallback_preview_id == "new-backing-agent"
assert calls[1] == {
"refresh": {
"tenant_id": "tenant-1",
"agent_id": "agent-1",
"account_id": "account-1",
"draft_type": AgentConfigDraftType.DRAFT,
}
}
assert calls[3] == {"get_app_backing_agent": {"tenant_id": "tenant-1", "app_id": "app-1"}}
assert calls[4] == {
"get_or_create": {"tenant_id": "tenant-1", "agent_id": "backing-agent", "account_id": "account-1"}
"get_or_create": {
"tenant_id": "tenant-1",
"agent_id": "backing-agent",
"account_id": "account-1",
"draft_type": AgentConfigDraftType.DEBUG_BUILD,
}
}
assert calls[6] == {"get_app_backing_agent": {"tenant_id": "tenant-1", "app_id": "app-1"}}
assert calls[7] == {
"refresh": {
"tenant_id": "tenant-1",
"agent_id": "backing-agent",
"account_id": "account-1",
"draft_type": AgentConfigDraftType.DRAFT,
}
}
@@ -0,0 +1,150 @@
from types import SimpleNamespace
from unittest.mock import MagicMock, patch
import pytest
from werkzeug.exceptions import Forbidden
from controllers.console.app.error import AppNotFoundError
from controllers.console.app.wraps import agent_manage_required_for_agent_app
from core.rbac import RBACPermission, RBACResourceScope
from models.agent import AgentScope
TENANT_ID = "tenant-1"
ACCOUNT = SimpleNamespace(id="account-1")
def _guarded_view():
calls: list[dict[str, object]] = []
@agent_manage_required_for_agent_app
def view(*args, **kwargs):
calls.append(kwargs)
return "ok"
return view, calls
def _app_with_binding(binding):
app_model = MagicMock()
app_model.agent_app_binding_with_session.return_value = binding
return app_model
def _patch_guard(app_model, rbac_enabled: bool):
mock_db = MagicMock()
mock_db.session.scalar.return_value = app_model
return (
patch("controllers.console.app.wraps.db", mock_db),
patch("controllers.console.app.wraps.current_account_with_tenant", return_value=(ACCOUNT, TENANT_ID)),
patch("controllers.console.app.wraps.dify_config.RBAC_ENABLED", rbac_enabled),
)
class TestAgentManageRequiredForAgentApp:
def test_non_agent_app_passes_through_without_workspace_check(self):
view, calls = _guarded_view()
patches = _patch_guard(_app_with_binding(None), rbac_enabled=True)
with patches[0], patches[1], patches[2], patch("controllers.console.app.wraps.enforce_rbac_access") as gate:
assert view(app_id="app-1") == "ok"
gate.assert_not_called()
assert calls == [{"app_id": "app-1"}]
def test_roster_agent_app_requires_agent_manage_when_rbac_enabled(self):
view, _ = _guarded_view()
binding = SimpleNamespace(scope=AgentScope.ROSTER)
patches = _patch_guard(_app_with_binding(binding), rbac_enabled=True)
with patches[0], patches[1], patches[2], patch("controllers.console.app.wraps.enforce_rbac_access") as gate:
assert view(app_id="app-1") == "ok"
gate.assert_called_once_with(
tenant_id=TENANT_ID,
account_id=ACCOUNT.id,
resource_type=RBACResourceScope.WORKSPACE,
scene=RBACPermission.AGENT_MANAGE,
resource_required=False,
)
def test_roster_agent_app_denied_without_agent_manage(self):
view, calls = _guarded_view()
binding = SimpleNamespace(scope=AgentScope.ROSTER)
patches = _patch_guard(_app_with_binding(binding), rbac_enabled=True)
with (
patches[0],
patches[1],
patches[2],
patch("controllers.console.app.wraps.enforce_rbac_access", side_effect=Forbidden()),
):
with pytest.raises(Forbidden):
view(app_id="app-1")
assert calls == []
def test_roster_agent_app_skips_workspace_check_when_rbac_disabled(self):
view, _ = _guarded_view()
binding = SimpleNamespace(scope=AgentScope.ROSTER)
patches = _patch_guard(_app_with_binding(binding), rbac_enabled=False)
with patches[0], patches[1], patches[2], patch("controllers.console.app.wraps.enforce_rbac_access") as gate:
assert view(app_id="app-1") == "ok"
gate.assert_not_called()
def test_hidden_backing_app_is_rejected_even_without_rbac(self):
"""A workflow-only backing App is not part of the general app management plane."""
view, calls = _guarded_view()
binding = SimpleNamespace(scope=AgentScope.WORKFLOW_ONLY)
patches = _patch_guard(_app_with_binding(binding), rbac_enabled=False)
with patches[0], patches[1], patches[2]:
with pytest.raises(AppNotFoundError):
view(app_id="app-1")
assert calls == []
def test_hidden_backing_app_is_rejected_before_workspace_check(self):
view, calls = _guarded_view()
binding = SimpleNamespace(scope=AgentScope.WORKFLOW_ONLY)
patches = _patch_guard(_app_with_binding(binding), rbac_enabled=True)
with patches[0], patches[1], patches[2], patch("controllers.console.app.wraps.enforce_rbac_access") as gate:
with pytest.raises(AppNotFoundError):
view(app_id="app-1")
gate.assert_not_called()
assert calls == []
def test_binding_lookup_covers_archived_agents(self):
"""An Agent App stays gated after its roster Agent is archived."""
view, _ = _guarded_view()
app_model = _app_with_binding(SimpleNamespace(scope=AgentScope.ROSTER))
patches = _patch_guard(app_model, rbac_enabled=True)
with patches[0], patches[1], patches[2], patch("controllers.console.app.wraps.enforce_rbac_access"):
view(app_id="app-1")
_, call_kwargs = app_model.agent_app_binding_with_session.call_args
assert call_kwargs["include_archived"] is True
def test_resource_id_path_alias_is_resolved(self):
view, _ = _guarded_view()
binding = SimpleNamespace(scope=AgentScope.ROSTER)
patches = _patch_guard(_app_with_binding(binding), rbac_enabled=True)
with patches[0], patches[1], patches[2], patch("controllers.console.app.wraps.enforce_rbac_access") as gate:
assert view(resource_id="app-1") == "ok"
gate.assert_called_once()
def test_unknown_app_passes_through_for_downstream_handling(self):
view, calls = _guarded_view()
patches = _patch_guard(None, rbac_enabled=True)
with patches[0], patches[1], patches[2], patch("controllers.console.app.wraps.enforce_rbac_access") as gate:
assert view(app_id="app-1") == "ok"
gate.assert_not_called()
assert calls == [{"app_id": "app-1"}]
@@ -9,13 +9,14 @@ from unittest.mock import MagicMock
import pytest
from flask import Flask
from sqlalchemy import event
from sqlalchemy import Engine, event
from sqlalchemy.orm import Session
from controllers.console.app import app_import as app_import_module
from models.account import Account
from models.base import TypeBase
from models.engine import db
from models.model import App
from models.model import App, AppMode
from services.app_dsl_service import ImportStatus
from services.entities.dsl_entities import CheckDependenciesResult
from services.feature_service import SystemFeatureModel, WebAppAuthModel
@@ -66,6 +67,13 @@ def app() -> Iterator[Flask]:
yield app
@pytest.fixture
def sqlite_app_engine(app: Flask) -> Engine:
engine = db.engine
TypeBase.metadata.create_all(engine, tables=[TypeBase.metadata.tables[App.__tablename__]])
return engine
@dataclass
class TransactionEvents:
commits: int = 0
@@ -93,11 +101,34 @@ def transaction_events() -> TransactionEvents:
event.remove(Session, "after_rollback", record_rollback)
def _failed_result_after_starting_transaction(
service: app_import_module.AppDslService, *, app_id: str | None = None
) -> _Result:
service._session.begin()
return _Result(ImportStatus.FAILED, app_id=app_id)
def _install_persisting_service_result(
monkeypatch: pytest.MonkeyPatch,
*,
method_name: str,
result: _Result,
) -> str:
app_id = result.app_id or "rolled-back-app"
def _return_result(import_service: app_import_module.AppDslService, *_args, **_kwargs):
import_service._session.add(
App(
id=app_id,
tenant_id="tenant-1",
name="Imported App",
mode=AppMode.WORKFLOW,
enable_site=True,
enable_api=True,
)
)
return result
monkeypatch.setattr(app_import_module.AppDslService, method_name, _return_result)
return app_id
def _assert_app_persistence(sqlite_app_engine: Engine, app_id: str, *, persisted: bool) -> None:
with Session(sqlite_app_engine) as session:
assert (session.get(App, app_id) is not None) is persisted
class TestAppImportApi:
@@ -110,15 +141,16 @@ class TestAppImportApi:
api,
app: Flask,
monkeypatch: pytest.MonkeyPatch,
sqlite_app_engine: Engine,
transaction_events: TransactionEvents,
) -> None:
method = unwrap(api.post)
_install_features(monkeypatch, enabled=False)
monkeypatch.setattr(
app_import_module.AppDslService,
"import_app",
lambda service, *_args, **_kwargs: _failed_result_after_starting_transaction(service, app_id=None),
app_id = _install_persisting_service_result(
monkeypatch,
method_name="import_app",
result=_Result(ImportStatus.FAILED, app_id=None),
)
with app.test_request_context("/console/api/apps/imports", method="POST", json={"mode": "yaml-content"}):
@@ -126,6 +158,7 @@ class TestAppImportApi:
assert transaction_events.rollbacks == 1
assert transaction_events.commits == 0
_assert_app_persistence(sqlite_app_engine, app_id, persisted=False)
assert status == 400
assert response["status"] == ImportStatus.FAILED
@@ -134,15 +167,16 @@ class TestAppImportApi:
api,
app: Flask,
monkeypatch: pytest.MonkeyPatch,
sqlite_app_engine: Engine,
transaction_events: TransactionEvents,
) -> None:
method = unwrap(api.post)
_install_features(monkeypatch, enabled=False)
monkeypatch.setattr(
app_import_module.AppDslService,
"import_app",
lambda *_args, **_kwargs: _Result(ImportStatus.PENDING),
app_id = _install_persisting_service_result(
monkeypatch,
method_name="import_app",
result=_Result(ImportStatus.PENDING),
)
with app.test_request_context("/console/api/apps/imports", method="POST", json={"mode": "yaml-content"}):
@@ -150,6 +184,7 @@ class TestAppImportApi:
assert transaction_events.commits == 1
assert transaction_events.rollbacks == 0
_assert_app_persistence(sqlite_app_engine, app_id, persisted=True)
assert status == 202
assert response["status"] == ImportStatus.PENDING
@@ -158,15 +193,16 @@ class TestAppImportApi:
api,
app: Flask,
monkeypatch: pytest.MonkeyPatch,
sqlite_app_engine: Engine,
transaction_events: TransactionEvents,
) -> None:
method = unwrap(api.post)
_install_features(monkeypatch, enabled=True)
monkeypatch.setattr(
app_import_module.AppDslService,
"import_app",
lambda *_args, **_kwargs: _Result(ImportStatus.COMPLETED, app_id="app-123"),
app_id = _install_persisting_service_result(
monkeypatch,
method_name="import_app",
result=_Result(ImportStatus.COMPLETED, app_id="app-123"),
)
update_access = MagicMock()
monkeypatch.setattr(app_import_module.EnterpriseService.WebAppAuth, "update_app_access_mode", update_access)
@@ -176,6 +212,7 @@ class TestAppImportApi:
assert transaction_events.commits == 1
assert transaction_events.rollbacks == 0
_assert_app_persistence(sqlite_app_engine, app_id, persisted=True)
update_access.assert_called_once_with("app-123", "private")
assert status == 200
assert response["status"] == ImportStatus.COMPLETED
@@ -185,6 +222,7 @@ class TestAppImportApi:
api,
app: Flask,
monkeypatch: pytest.MonkeyPatch,
sqlite_app_engine: Engine,
transaction_events: TransactionEvents,
) -> None:
method = _unwrap(api.post)
@@ -196,10 +234,10 @@ class TestAppImportApi:
lambda: (_make_account(), "tenant-1"),
)
monkeypatch.setattr(app_import_module.dify_config, "RBAC_ENABLED", True)
monkeypatch.setattr(
app_import_module.AppDslService,
"import_app",
lambda *_args, **_kwargs: _Result(ImportStatus.COMPLETED, app_id="app-123"),
app_id = _install_persisting_service_result(
monkeypatch,
method_name="import_app",
result=_Result(ImportStatus.COMPLETED, app_id="app-123"),
)
monkeypatch.setattr(
app_import_module,
@@ -211,6 +249,7 @@ class TestAppImportApi:
response, status = method()
assert transaction_events.commits == 1
_assert_app_persistence(sqlite_app_engine, app_id, persisted=True)
assert status == 200
assert response["permission_keys"] == ["app.acl.view_layout", "app.acl.edit"]
@@ -219,6 +258,7 @@ class TestAppImportApi:
api,
app: Flask,
monkeypatch: pytest.MonkeyPatch,
sqlite_app_engine: Engine,
transaction_events: TransactionEvents,
) -> None:
method = _unwrap(api.post)
@@ -230,10 +270,10 @@ class TestAppImportApi:
lambda: (_make_account(), "tenant-1"),
)
monkeypatch.setattr(app_import_module.dify_config, "RBAC_ENABLED", True)
monkeypatch.setattr(
app_import_module.AppDslService,
"import_app",
lambda *_args, **_kwargs: _Result(ImportStatus.COMPLETED, app_id="app-123"),
app_id = _install_persisting_service_result(
monkeypatch,
method_name="import_app",
result=_Result(ImportStatus.COMPLETED, app_id="app-123"),
)
monkeypatch.setattr(
app_import_module,
@@ -249,6 +289,7 @@ class TestAppImportApi:
response, status = method()
assert transaction_events.commits == 1
_assert_app_persistence(sqlite_app_engine, app_id, persisted=True)
assert status == 200
assert response["permission_keys"] == []
@@ -263,14 +304,15 @@ class TestAppImportConfirmApi:
api,
app: Flask,
monkeypatch: pytest.MonkeyPatch,
sqlite_app_engine: Engine,
transaction_events: TransactionEvents,
) -> None:
method = unwrap(api.post)
monkeypatch.setattr(
app_import_module.AppDslService,
"confirm_import",
lambda service, *_args, **_kwargs: _failed_result_after_starting_transaction(service),
app_id = _install_persisting_service_result(
monkeypatch,
method_name="confirm_import",
result=_Result(ImportStatus.FAILED),
)
with app.test_request_context("/console/api/apps/imports/import-1/confirm", method="POST"):
@@ -278,6 +320,7 @@ class TestAppImportConfirmApi:
assert transaction_events.rollbacks == 1
assert transaction_events.commits == 0
_assert_app_persistence(sqlite_app_engine, app_id, persisted=False)
assert status == 400
assert response["status"] == ImportStatus.FAILED
@@ -286,6 +329,7 @@ class TestAppImportConfirmApi:
api,
app: Flask,
monkeypatch: pytest.MonkeyPatch,
sqlite_app_engine: Engine,
transaction_events: TransactionEvents,
) -> None:
method = _unwrap(api.post)
@@ -304,10 +348,10 @@ class TestAppImportConfirmApi:
),
)
monkeypatch.setattr(app_import_module.dify_config, "RBAC_ENABLED", True)
monkeypatch.setattr(
app_import_module.AppDslService,
"confirm_import",
lambda *_args, **_kwargs: _Result(ImportStatus.COMPLETED, app_id="app-456"),
app_id = _install_persisting_service_result(
monkeypatch,
method_name="confirm_import",
result=_Result(ImportStatus.COMPLETED, app_id="app-456"),
)
monkeypatch.setattr(
app_import_module,
@@ -319,6 +363,7 @@ class TestAppImportConfirmApi:
response, status = method(import_id="import-1")
assert transaction_events.commits == 1
_assert_app_persistence(sqlite_app_engine, app_id, persisted=True)
assert status == 200
assert response["permission_keys"] == ["app.acl.view_layout", "app.acl.edit"]
@@ -327,6 +372,7 @@ class TestAppImportConfirmApi:
api,
app: Flask,
monkeypatch: pytest.MonkeyPatch,
sqlite_app_engine: Engine,
transaction_events: TransactionEvents,
) -> None:
method = _unwrap(api.post)
@@ -345,10 +391,10 @@ class TestAppImportConfirmApi:
),
)
monkeypatch.setattr(app_import_module.dify_config, "RBAC_ENABLED", True)
monkeypatch.setattr(
app_import_module.AppDslService,
"confirm_import",
lambda *_args, **_kwargs: _Result(ImportStatus.COMPLETED, app_id="app-456"),
app_id = _install_persisting_service_result(
monkeypatch,
method_name="confirm_import",
result=_Result(ImportStatus.COMPLETED, app_id="app-456"),
)
monkeypatch.setattr(
app_import_module,
@@ -360,6 +406,7 @@ class TestAppImportConfirmApi:
response, status = method(import_id="import-1")
assert transaction_events.commits == 1
_assert_app_persistence(sqlite_app_engine, app_id, persisted=True)
assert status == 200
assert response["permission_keys"] == []
@@ -1,5 +1,6 @@
import pytest
from flask import Flask
from sqlalchemy.orm import Session
from controllers.console.app import generator as generator_module
from core.errors.error import ModelCurrentlyNotSupportError, ProviderTokenNotInitError, QuotaExceededError
@@ -102,12 +103,14 @@ def test_structured_output_generate_exceptions(app: Flask, monkeypatch: pytest.M
method(api, "t1")
def test_instruction_generate_exceptions(app: Flask, monkeypatch: pytest.MonkeyPatch) -> None:
@pytest.mark.parametrize("sqlite_session", [()], indirect=True)
def test_instruction_generate_exceptions(
app: Flask,
monkeypatch: pytest.MonkeyPatch,
sqlite_session: Session,
) -> None:
api = generator_module.InstructionGenerateApi()
method = unwrap(api.post)
from types import SimpleNamespace
session = SimpleNamespace()
exceptions_to_test = [
(ProviderTokenNotInitError("token error"), generator_module.ProviderNotInitializeError),
@@ -135,4 +138,4 @@ def test_instruction_generate_exceptions(app: Flask, monkeypatch: pytest.MonkeyP
},
):
with pytest.raises(expected_exception):
method(api, session, "t1")
method(api, sqlite_session, "t1")
@@ -11,7 +11,7 @@ import pytest
from flask import Flask
from sqlalchemy import func, select
from sqlalchemy.engine import Engine
from sqlalchemy.orm import object_session, sessionmaker
from sqlalchemy.orm import Session, object_session, sessionmaker
from controllers.common import session as controller_session
from controllers.console.app import model_config as model_config_module
@@ -29,11 +29,14 @@ def _poison_implicit_app_config_properties(monkeypatch: pytest.MonkeyPatch) -> N
@pytest.mark.parametrize("app_mode", [AppMode.CHAT, AppMode.COMPLETION])
@pytest.mark.parametrize("sqlite_session", [(AppModelConfig,)], indirect=True)
def test_post_updates_non_agent_model_config_without_implicit_properties(
app: Flask,
monkeypatch: pytest.MonkeyPatch,
app_mode: AppMode,
sqlite_session: Session,
) -> None:
"""Flush a non-agent config through the injected session without legacy model properties."""
api = model_config_module.ModelConfigResource()
method = unwrap(api.post)
@@ -45,14 +48,16 @@ def test_post_updates_non_agent_model_config_without_implicit_properties(
updated_at=None,
)
original_config = AppModelConfig(app_id="app-1", created_by="u1", updated_by="u1")
original_config.id = "config-0"
original_config.agent_mode = None
sqlite_session.add(original_config)
sqlite_session.commit()
_poison_implicit_app_config_properties(monkeypatch)
monkeypatch.setattr(
model_config_module.AppModelConfigService,
"validate_configuration",
lambda **_kwargs: {"pre_prompt": "hi"},
)
session = MagicMock()
def _from_model_config_dict(self, model_config):
self.pre_prompt = model_config["pre_prompt"]
@@ -62,18 +67,16 @@ def test_post_updates_non_agent_model_config_without_implicit_properties(
monkeypatch.setattr(AppModelConfig, "from_model_config_dict", _from_model_config_dict)
send_mock = MagicMock()
monkeypatch.setattr(model_config_module.app_model_config_was_updated, "send", send_mock)
session.get.return_value = original_config
with app.test_request_context("/console/api/apps/app-1/model-config", method="POST", json={"pre_prompt": "hi"}):
response = method(api, session, "t1", "u1", app_model=app_model)
response = method(api, sqlite_session, "t1", "u1", app_model=app_model)
session.get.assert_called_once_with(AppModelConfig, "config-0")
session.add.assert_called_once()
session.flush.assert_called_once()
session.commit.assert_not_called()
assert send_mock.call_args.kwargs["session"] is session
assert send_mock.call_args.kwargs["session"] is sqlite_session
assert app_model.app_model_config_id == "config-1"
assert app_model.mode == app_mode
persisted_config = sqlite_session.get(AppModelConfig, "config-1")
assert persisted_config is not None
assert persisted_config.pre_prompt == "hi"
assert response["result"] == "success"
@@ -160,7 +163,11 @@ def test_post_uses_one_session_and_rolls_back_when_signal_fails(
assert config_count == 1
def test_post_encrypts_agent_tool_parameters(app: Flask, monkeypatch: pytest.MonkeyPatch) -> None:
@pytest.mark.parametrize("sqlite_session", [(AppModelConfig,)], indirect=True)
def test_post_encrypts_agent_tool_parameters(
app: Flask, monkeypatch: pytest.MonkeyPatch, sqlite_session: Session
) -> None:
"""Agent parameter encryption reads and writes persisted model configurations."""
api = model_config_module.ModelConfigResource()
method = unwrap(api.post)
@@ -174,6 +181,7 @@ def test_post_encrypts_agent_tool_parameters(app: Flask, monkeypatch: pytest.Mon
_poison_implicit_app_config_properties(monkeypatch)
original_config = AppModelConfig(app_id="app-1", created_by="u1", updated_by="u1")
original_config.id = "config-0"
original_config.agent_mode = json.dumps(
{
"enabled": True,
@@ -190,8 +198,8 @@ def test_post_encrypts_agent_tool_parameters(app: Flask, monkeypatch: pytest.Mon
}
)
session = MagicMock()
session.scalar.return_value = original_config
sqlite_session.add(original_config)
sqlite_session.commit()
monkeypatch.setattr(
model_config_module.AppModelConfigService,
@@ -236,11 +244,11 @@ def test_post_encrypts_agent_tool_parameters(app: Flask, monkeypatch: pytest.Mon
monkeypatch.setattr(model_config_module.app_model_config_was_updated, "send", send_mock)
with app.test_request_context("/console/api/apps/app-1/model-config", method="POST", json={"pre_prompt": "hi"}):
response = method(api, session, "t1", "u1", app_model=app_model)
response = method(api, sqlite_session, "t1", "u1", app_model=app_model)
stored_config = session.add.call_args[0][0]
stored_config = sqlite_session.get(AppModelConfig, app_model.app_model_config_id)
assert stored_config is not None
stored_agent_mode = json.loads(stored_config.agent_mode)
session.scalar.assert_called_once()
assert app_model.mode == AppMode.AGENT_CHAT
assert stored_agent_mode["tools"][0]["tool_parameters"]["secret"] == "encrypted"
assert response["result"] == "success"
@@ -14,6 +14,7 @@ import pytest
from flask import Flask
from controllers.console.auth.activate import ActivateApi, ActivateCheckApi
from controllers.console.auth.error import InvitationAccountMismatchError
from controllers.console.error import AccountInFreezeError, AlreadyActivateError
from models.account import AccountStatus, TenantAccountRole
@@ -202,6 +203,50 @@ class TestActivateApi:
with patch("controllers.console.auth.activate.TenantService.switch_tenant") as mock:
yield mock
@patch("controllers.console.auth.activate.TenantService.create_tenant_member")
@patch("controllers.console.auth.activate.RegisterService.get_invitation_with_case_fallback")
@patch("controllers.console.auth.activate.RegisterService.revoke_token")
@patch("controllers.console.auth.activate.current_account_with_tenant")
@patch("controllers.console.auth.activate.extract_access_token", return_value="access-token")
@patch("controllers.console.auth.activate.db")
def test_activation_rejects_invitation_for_different_authenticated_account(
self,
mock_db: MagicMock,
mock_extract_access_token: MagicMock,
mock_current_account_with_tenant: MagicMock,
mock_revoke_token: MagicMock,
mock_get_invitation: MagicMock,
mock_create_tenant_member: MagicMock,
app: Flask,
mock_invitation: MagicMock,
mock_account: MagicMock,
mock_switch_tenant: MagicMock,
):
"""A logged-in account cannot consume another account's invitation token."""
current_account = MagicMock()
current_account.id = "current-account-id"
mock_account.id = "invited-account-id"
mock_account.status = AccountStatus.ACTIVE
mock_invitation["data"]["requires_setup"] = False
mock_get_invitation.return_value = mock_invitation
mock_current_account_with_tenant.return_value = (current_account, "current-workspace-id")
with app.test_request_context(
"/activate",
method="POST",
json={
"token": "valid_token",
},
):
with pytest.raises(InvitationAccountMismatchError):
ActivateApi().post()
mock_extract_access_token.assert_called_once()
mock_revoke_token.assert_not_called()
mock_create_tenant_member.assert_not_called()
mock_switch_tenant.assert_not_called()
mock_db.session.scalar.assert_not_called()
@patch("controllers.console.auth.activate.RegisterService.get_invitation_if_token_valid")
@patch("controllers.console.auth.activate.RegisterService.revoke_token")
@patch("controllers.console.auth.activate.db")
@@ -1,4 +1,4 @@
"""Testcontainers integration tests for OAuth controller endpoints."""
"""Unit tests for OAuth controller endpoints."""
from __future__ import annotations
@@ -16,15 +16,10 @@ from controllers.console.auth.oauth import (
)
from libs.oauth import OAuthUserInfo, encode_oauth_state
from models.account import AccountStatus
from services.account_service import AccountService
from services.errors.account import AccountRegisterError
class TestGetOAuthProviders:
@pytest.fixture
def app(self, flask_app_with_containers: Flask):
return flask_app_with_containers
@pytest.mark.parametrize(
("github_config", "google_config", "expected_github", "expected_google"),
[
@@ -65,10 +60,6 @@ class TestOAuthLogin:
def resource(self):
return OAuthLogin()
@pytest.fixture
def app(self, flask_app_with_containers: Flask):
return flask_app_with_containers
@pytest.fixture
def mock_oauth_provider(self):
provider = MagicMock()
@@ -181,10 +172,6 @@ class TestOAuthCallback:
def resource(self):
return OAuthCallback()
@pytest.fixture
def app(self, flask_app_with_containers: Flask):
return flask_app_with_containers
@pytest.fixture
def oauth_setup(self):
"""Common OAuth setup for callback tests"""
@@ -263,10 +250,12 @@ class TestOAuthCallback:
@patch("controllers.console.auth.oauth.dify_config")
@patch("controllers.console.auth.oauth.get_oauth_providers")
@patch("controllers.console.auth.oauth.RegisterService")
@patch("controllers.console.auth.oauth.AccountService")
@patch("controllers.console.auth.oauth.redirect")
def test_invitation_comparison_is_case_insensitive(
self,
mock_redirect,
mock_account_service,
mock_register_service,
mock_get_providers,
mock_config,
@@ -280,13 +269,20 @@ class TestOAuthCallback:
)
mock_get_providers.return_value = {"github": oauth_setup["provider"]}
mock_register_service.is_valid_invite_token.return_value = True
mock_register_service.get_invitation_by_token.return_value = {"email": "user@example.com"}
mock_register_service.get_invitation_if_token_valid.return_value = {
"account": oauth_setup["account"],
"data": {"email": "user@example.com"},
"tenant": MagicMock(),
}
mock_account_service.login.return_value = oauth_setup["token_pair"]
state = encode_oauth_state(invite_token="invite123", timezone="Asia/Shanghai")
with app.test_request_context(f"/auth/oauth/github/callback?code=test_code&state={state}"):
resource.get("github")
mock_register_service.get_invitation_by_token.assert_called_once_with(token="invite123")
mock_register_service.get_invitation_if_token_valid.assert_called_once_with(
None, None, "invite123", session=ANY
)
mock_redirect.assert_called_once_with("http://localhost:3000/signin/invite-settings?invite_token=invite123")
@pytest.mark.parametrize(
@@ -448,10 +444,6 @@ class TestOAuthCallback:
class TestAccountGeneration:
@pytest.fixture
def app(self, flask_app_with_containers: Flask):
return flask_app_with_containers
@pytest.fixture
def user_info(self):
return OAuthUserInfo(id="123", name="Test User", email="test@example.com")
@@ -468,39 +460,25 @@ class TestAccountGeneration:
self,
mock_account_model,
mock_get_account,
flask_req_ctx_with_containers,
app: Flask,
user_info: OAuthUserInfo,
mock_account,
):
# Test OpenID found
mock_account_model.get_by_openid.return_value = mock_account
result = _get_account_by_openid_or_email("github", user_info)
assert result == mock_account
mock_account_model.get_by_openid.assert_called_once_with("github", "123")
mock_get_account.assert_not_called()
with app.test_request_context("/"):
# Test OpenID found
mock_account_model.get_by_openid.return_value = mock_account
result = _get_account_by_openid_or_email("github", user_info)
assert result == mock_account
mock_account_model.get_by_openid.assert_called_once_with("github", "123")
mock_get_account.assert_not_called()
# Test fallback to email lookup
mock_account_model.get_by_openid.return_value = None
mock_get_account.return_value = mock_account
# Test fallback to email lookup
mock_account_model.get_by_openid.return_value = None
mock_get_account.return_value = mock_account
result = _get_account_by_openid_or_email("github", user_info)
assert result == mock_account
mock_get_account.assert_called_once()
def test_get_account_by_email_with_case_fallback_falls_back_to_lowercase(self):
"""Test that case fallback tries lowercase when exact match fails."""
mock_session = MagicMock()
first_result = MagicMock()
first_result.scalar_one_or_none.return_value = None
expected_account = MagicMock()
second_result = MagicMock()
second_result.scalar_one_or_none.return_value = expected_account
mock_session.execute.side_effect = [first_result, second_result]
result = AccountService.get_account_by_email_with_case_fallback("Case@Test.com", session=mock_session)
assert result is expected_account
assert mock_session.execute.call_count == 2
result = _get_account_by_openid_or_email("github", user_info)
assert result == mock_account
mock_get_account.assert_called_once()
@pytest.mark.parametrize(
("allow_register", "existing_account", "should_create"),
@@ -1,5 +1,5 @@
import urllib.parse
from unittest.mock import MagicMock, patch
from unittest.mock import ANY, MagicMock, patch
import pytest
from flask import Flask
@@ -91,3 +91,102 @@ def test_oauth_callback_validates_redirect_url_and_appends_new_user_flag(
assert response.headers["Location"] == (
f"{expected_target_url}{query_char}oauth_new_user={str(oauth_new_user).lower()}"
)
def test_oauth_callback_with_invitation_establishes_console_session(app: Flask) -> None:
oauth_provider = MagicMock()
oauth_provider.get_access_token.return_value = "google-access-token"
oauth_provider.get_user_info.return_value = OAuthUserInfo(
id="google-user-123",
name="Test User",
email="Invitee@Example.com",
)
account = MagicMock()
account.status = AccountStatus.ACTIVE
token_pair = MagicMock()
token_pair.access_token = "dify-access-token"
token_pair.refresh_token = "dify-refresh-token"
token_pair.csrf_token = "dify-csrf-token"
state = encode_oauth_state(invite_token="invite-token")
with (
patch("controllers.console.auth.oauth.get_oauth_providers", return_value={"google": oauth_provider}),
patch("controllers.console.auth.oauth.dify_config.CONSOLE_WEB_URL", CONSOLE_WEB_URL),
patch("controllers.console.auth.oauth.RegisterService") as register_service,
patch("controllers.console.auth.oauth.AccountService.link_account_integrate") as link_account,
patch("controllers.console.auth.oauth.AccountService.login", return_value=token_pair) as login,
patch("controllers.console.auth.oauth.TenantService.create_owner_tenant_if_not_exist") as create_workspace,
patch("controllers.console.auth.oauth.set_access_token_to_cookie") as set_access_cookie,
patch("controllers.console.auth.oauth.set_refresh_token_to_cookie") as set_refresh_cookie,
patch("controllers.console.auth.oauth.set_csrf_token_to_cookie") as set_csrf_cookie,
app.test_request_context(f"/oauth/authorize/google?code=test-code&state={state}"),
):
register_service.is_valid_invite_token.return_value = True
register_service.get_invitation_if_token_valid.return_value = {
"account": account,
"data": {
"account_id": "account-id",
"email": "invitee@example.com",
"workspace_id": "workspace-id",
},
"tenant": MagicMock(),
}
response = OAuthCallback().get("google")
assert response.status_code == 302
assert response.headers["Location"] == (f"{CONSOLE_WEB_URL}/signin/invite-settings?invite_token=invite-token")
link_account.assert_called_once_with("google", "google-user-123", account, session=ANY)
login.assert_called_once_with(account=account, session=ANY, ip_address=ANY)
create_workspace.assert_not_called()
set_access_cookie.assert_called_once_with(ANY, response, "dify-access-token")
set_refresh_cookie.assert_called_once_with(ANY, response, "dify-refresh-token")
set_csrf_cookie.assert_called_once_with(ANY, response, "dify-csrf-token")
def test_oauth_callback_with_invitation_rejects_another_account(app: Flask) -> None:
oauth_provider = MagicMock()
oauth_provider.get_access_token.return_value = "google-access-token"
oauth_provider.get_user_info.return_value = OAuthUserInfo(
id="google-user-123",
name="Test User",
email="another@example.com",
)
account = MagicMock()
account.status = AccountStatus.ACTIVE
state = encode_oauth_state(invite_token="invite-token")
with (
patch("controllers.console.auth.oauth.get_oauth_providers", return_value={"google": oauth_provider}),
patch("controllers.console.auth.oauth.dify_config.CONSOLE_WEB_URL", CONSOLE_WEB_URL),
patch("controllers.console.auth.oauth.RegisterService") as register_service,
patch("controllers.console.auth.oauth.AccountService.link_account_integrate") as link_account,
patch("controllers.console.auth.oauth.AccountService.login") as login,
patch("controllers.console.auth.oauth.set_access_token_to_cookie") as set_access_cookie,
patch("controllers.console.auth.oauth.set_refresh_token_to_cookie") as set_refresh_cookie,
patch("controllers.console.auth.oauth.set_csrf_token_to_cookie") as set_csrf_cookie,
app.test_request_context(f"/oauth/authorize/google?code=test-code&state={state}"),
):
register_service.is_valid_invite_token.return_value = True
register_service.get_invitation_if_token_valid.return_value = {
"account": account,
"data": {
"account_id": "account-id",
"email": "invitee@example.com",
"workspace_id": "workspace-id",
},
"tenant": MagicMock(),
}
response = OAuthCallback().get("google")
query = urllib.parse.parse_qs(urllib.parse.urlparse(response.headers["Location"]).query)
assert response.status_code == 302
assert query["message"] == ["This invitation was sent to another account. Please sign in with the invited account."]
assert query["invite_token"] == ["invite-token"]
link_account.assert_not_called()
login.assert_not_called()
register_service.revoke_token.assert_not_called()
set_access_cookie.assert_not_called()
set_refresh_cookie.assert_not_called()
set_csrf_cookie.assert_not_called()
@@ -3,7 +3,7 @@ from __future__ import annotations
from inspect import unwrap
from unittest.mock import patch
from controllers.console.auth.oauth_server import OAuthServerUserAuthorizeApi
from controllers.console.auth.oauth_server import OAuthServerUserAccountApi, OAuthServerUserAuthorizeApi
from models import Account
from models.account import AccountStatus, TenantAccountRole
from models.model import OAuthProviderApp
@@ -45,3 +45,13 @@ def test_oauth_authorize_uses_injected_current_user() -> None:
sign_oauth_authorization_code.assert_called_once_with("client-1", "account-1")
assert response == {"code": "authorization-code"}
def test_oauth_account_returns_stable_account_id() -> None:
api = OAuthServerUserAccountApi()
method = unwrap(api.post)
account = _make_account()
response = method(api, _make_oauth_provider_app(), account)
assert response["id"] == "account-1"

Some files were not shown because too many files have changed in this diff Show More