WEBDIENSTE/langgraph
1
0
Fork 0
mirror of https://github.com/langchain-ai/langgraph.git synced 2026-09-26 11:35:02 +02:00
Code Issues Packages Projects Releases Wiki Activity
7,088 Commits 331 Branches 576 Tags
4d5bb3c26e208f3fd97c267985e96da170e51a42
Commit Graph
100 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Nuno Campos 417103066b Lint 2025-06-16 09:29:03 -07:00
Nuno Campos 25a59447c1 Introduce "tasks" and "checkpoints" stream modes 
- These are split out of "debug" stream mode, which is now an alias for ["tasks", "checkpoints"]
 2025-06-16 08:47:45 -07:00
Nuno Campos b95267a3cc Refine dependency map 2025-06-10 10:06:08 -07:00
Nuno Campos 5ab5da767b Pass tags when configuring async callback manager 2025-06-03 16:17:17 -07:00
Nuno Campos 7080eaa79e docs: fix ensure_config docstring 2025-06-03 15:56:41 -07:00
Nuno Campos cd2847ee07 docs: fix double article typos 2025-06-03 15:53:19 -07:00
Nuno Campos 936176eb21 Remove Checkpoint.writes 
- This has been superseded by saving the individual writes of each task through put_writes()
- Removing this speeds up checkpoint operations as it was duplicating data saved elsewhere already
 2025-05-25 19:06:46 -07:00
Nuno Campos 4e8fbe4525 Remove Checkpoint.pending_sends 
- Instead store sends in a Topic channel, removing the need to fetch sends as writes against the parent checkpoint
- Remove deprecated/unused functions in langgraph-checkpoint (will require bumping min range for langgraph-checkpoint in langgraph lib)
- Implement migration of old pending sends in langgraph-checkpoint-postgres
- Ensure parent config of `checkpoint_during=False` checkpoints always points to checkpoints that were also saved
 2025-05-25 19:06:02 -07:00
Nuno Campos 85522ec6a6 Pregel: Add NodeBuilder class to replace Channel.subscribe_to 
- For now keeping Channel.subscribe_to given it was used in docs
 2025-05-24 20:35:37 -07:00
Nuno Campos 0f8f5444bc Lint 2025-05-24 14:54:57 -07:00
Nuno Campos bc17c3522b Remove old checkpoint test fixtures 
- Now all tests fully migrated to more recent sync_checkpointer and async_checkpointer fixtures for parametrising on checkpointer
- Use sync/async_store fixtures where tests used only in memory store
- Remove unused "should snapshot" check for older versions of langchain core no longer tested against
 2025-05-24 14:27:13 -07:00
Nuno Campos 8c11c1155a Remove postgres shallow checkpointer 
- This was deprecated, and superseded by checkpoint_during=False, which is available for all checkpointers
 2025-05-24 12:39:50 -07:00
Nuno Campos 9c79d887a0 Remove ChannelsManager, ManagedValues are now static classes and never instantiated 
- This keeps the existing API for accessing IsLastValue, RemainingSteps, but simplifies the internal implementation
- This lets us remove ChannelsManager completely, which no longer needs to be a context manager, now replaced w function channels_from_checkpoint
- Managed values are now simple functions that return a value given a PregelScratchpad, which will be easier to implement in distributed runner
 2025-05-24 12:15:11 -07:00
Nuno Campos 889b40e7a8 Remove Context channel / managed value, Remove SharedValue 
- Both have been deprecated long ago, have not been present in docs for quite a while
- Removing these lets us delete some code paths that were dedicated to this, easing work on distributed runner
 2025-05-24 11:05:15 -07:00
Nuno CamposandNuno Campos 6fe319ed1b WIP: Add migrate_checkpoint 2025-04-02 07:24:55 -07:00
Nuno Campos 6efeefe424 Maintain checkpoint LATEST_VERSION constant in langgraph lib 
- This should be controlled by the langgraph version, not the version of langgraph-checkpoint installed
 2025-04-01 21:46:38 -07:00
Nuno Campos a541376d10 Store all triggers in task 
- These are used to update seen version
 2025-03-18 21:17:26 -07:00
Nuno CamposandNuno Campos 8bcdba822e Reduce to 4.1s 2025-03-18 09:15:28 -07:00
Nuno CamposandNuno Campos 60fc49b448 Speed up prepare_single_task 
- sequential(2000) goes from 8.4s to 4.7s
- replace UUID(str).bytes with simpler str.encode()
- find only the first active trigger, instead of the full list
- use a dedicated function for checking active trigger
 2025-03-18 09:15:11 -07:00
Nuno Campos 3f241d00a3 Fix bench 2025-03-18 06:45:41 -07:00
Nuno Campos d6a457ef1d Improve prepare_single_task trigger checks to linear complexity 
- Was O(n^2) due to individual channels created for every conditional edge, including the default cond edge created for Command
- Now using a single channel per node for all conditional edge / command triggers, reducing to linear complexity
- Improves run time on sequential(200) from 1.8s to 0.14s
 2025-03-17 21:26:26 -07:00
Nuno Campos ce1077da40 Speed up task triggers check 
- Using a sentinel value is faster than raising-catching an exception
 2025-03-17 21:04:05 -07:00
Nuno Campos 969958695a Add time when running directly 2025-03-17 20:59:10 -07:00
Nuno Campos dd16ae4ba5 When using global resume value, ensure subgraphs consume it 
- Previously the global resume value was passed to subgraphs without being consumed
- This would result in two parallel subgraph calls being able to use the same resume value
- Note this behavior can't be implemented over the wire, that will be fixed in future PR
 2025-03-17 20:31:54 -07:00
Nuno Campos eae1faa656 Fix 2025-03-17 20:12:33 -07:00
Nuno Campos 1976d6584c Lint 2025-03-17 20:00:33 -07:00
Nuno Campos 54e18445fc Fix concurrency issue in PregelScratchpad.consume_null_resume 
- Need to use a single operation to check if present and remove item from list
- This doesn't fix the separate issue that parallel tasks claiming a single interrupt value have somewhat undefined behavior (in the sense that they will race to be the first to take it). That will be fixed in a future PR
 2025-03-17 19:53:03 -07:00
Nuno Campos bad4d17c34 Remove 'check size' ci job 2025-03-14 21:54:01 -07:00
Nuno Campos 1bb0037450 langgraph: stream_mode=messages should not emit input or state messages 
- any messages seen in inputs in on_chain_start should not be emitted
 2025-02-25 19:00:33 -08:00
Nuno Campos 69ad42cac5 Add CONFIG_KEY_RUNNER_SUBMIT 2025-02-17 17:33:38 -08:00
Nuno Campos b5c659bc9f Resolve 2025-02-17 17:12:06 -08:00
Nuno Campos 4623f7b5da Fix 2025-02-17 17:09:31 -08:00
Nuno Campos d03ead2f43 Fix path in assertion 2025-02-17 11:47:38 -08:00
Nuno Campos 5a8624fdfd cli: Add support for dependencies in parent directories 
- Now supporting local dependencies in directories that are not contained in the docker context (ie. outside the folder containing langgraph.json)
- This is achieved by passing each parent directorty as an additional context to docker build
- This makes it a lot easier to build projects contained in monorepos where you need to include some sibling/parent folder as a dependency
- Also include additional comments in the generated dockerfile to delimit each section
 2025-02-17 11:43:55 -08:00
Nuno Campos 9786be1ff7 Update requirement 2025-02-14 19:01:50 -08:00
Nuno Campos 62f004fd28 Lint 2025-02-14 18:42:40 -08:00
Nuno Campos d4b22ac1d4 Fix postgres tests 2025-02-14 18:40:30 -08:00
Nuno Campos 0415c02b40 Fix sqlite tests 2025-02-14 18:34:06 -08:00
Nuno Campos e8665f84e7 Update 2025-02-14 18:31:03 -08:00
Nuno Campos 8ff5e79e70 Lint 2025-02-14 18:27:49 -08:00
Nuno Campos 7f4822931e Update tests 2025-02-14 18:24:48 -08:00
Nuno Campos b2213e523e Add get_store function 2025-01-20 16:03:27 -08:00
Nuno CamposandGitHub c865e8c070 Update README.md 2025-01-02 10:01:35 +00:00
Nuno CamposandGitHub 759a712f57 Merge pull request #2502 from langchain-ai/vb/fix-annotation 
langgraph: fix issue w/ type annotations in tools_condition
 2024-12-04 20:47:21 -05:00
Nuno CamposandGitHub 73e3f5a5b0 Merge pull request #2517 from langchain-ai/eugene/how_to_use_tempalte 
docs: Add template quickstart
 2024-12-04 20:37:04 -05:00
Nuno CamposandGitHub f32cf5e984 Merge pull request #2642 from langchain-ai/nc/4dec/fix-stream-params 
sdk-py: Handle stream(params=)
 2024-12-04 20:26:59 -05:00
Nuno CamposandGitHub b5a9e9da55 Merge pull request #2635 from langchain-ai/vb/add-graph-command-docs 
docs: add Command docs
 2024-12-04 20:14:35 -05:00
Nuno CamposandGitHub 574ffb02fc Merge pull request #2639 from langchain-ai/nc/4dec/speed-up-tests 
Speed up tests
 2024-12-04 18:37:03 -05:00
Nuno CamposandGitHub dcc2617396 Merge pull request #2638 from langchain-ai/nc/4dec/command 
lib: Merge GraphCommand and Command
 2024-12-04 18:26:11 -05:00
Nuno CamposandGitHub 78e6b36b1a Merge pull request #2636 from langchain-ai/nc/4dec/interrupt-loop 
lib: Add support for multiple interrupts per node
 2024-12-04 17:58:26 -05:00
Nuno CamposandGitHub 9ab5fbc0f8 Merge pull request #2627 from langchain-ai/nc/4dec/state-ensure-config 
lib: Call ensure_config in state crud methods
 2024-12-04 11:53:03 -05:00
Nuno CamposandGitHub 584d9271ce Merge pull request #2614 from langchain-ai/nc/3dec/handle-command 
Handle Command returned from node (in addition to GraphCommand)
 2024-12-03 19:05:05 -05:00
Nuno CamposandGitHub 86407aa6e8 Merge pull request #2071 from langchain-ai/brace/doc-nits 
fix(docs): Small nits & typo fixes
 2024-12-03 16:38:36 -05:00
Nuno CamposandGitHub 75cccc4fc4 Merge pull request #2589 from stneng/main 
fix: get correct reducer when type has multiple metadata.
 2024-12-03 16:23:33 -05:00
Nuno CamposandGitHub dd010e9230 Merge pull request #2593 from langchain-ai/nc/2dec/sdk-sse 
sdk-py: Fix SSE parsing to split lines only \n \r , remove httpx-sse, fix missing decoder flush
 2024-12-03 16:23:11 -05:00
Nuno CamposandGitHub 2d87195b59 Merge pull request #2611 from langchain-ai/vb/remote-graph-kwargs 
langgraph: allow passing kwargs to SDK methods in RemoteGraph's invoke/stream
 2024-12-03 16:21:09 -05:00
Nuno CamposandGitHub 64b99c187a Merge pull request #2544 from langchain-ai/brace/type-interrupts-py 
fix(sdk-py): Add typing for interrupts
 2024-12-02 20:52:19 -05:00
Nuno CamposandGitHub afa37d2059 Merge pull request #2552 from langchain-ai/vb/remove-assertion 
langgraph: relax graph validation to handle nodes without return typehints
 2024-12-02 20:51:50 -05:00
Nuno CamposandGitHub d70b659adb Merge pull request #2430 from langchain-ai/nc/15nov/command-subgraph 
Handle interrupt/resume for subgraphs
 2024-12-02 20:45:40 -05:00
Nuno Campos 4576a259dd sdk-py 0.1.39 2024-11-27 17:32:07 -08:00
Nuno Campos 53ec7c41b2 Revert "sdk-py: Fix SSE parsing to split lines only \n \r \r\n per SSE spec" 
This reverts commit dc09b13400.
 2024-11-27 17:31:21 -08:00
Nuno Campos 7866bd2718 lib: find_subgraph doesn't need to look in both func and afunc 
- if they both exist they're expected to share the same implementation, so looking in both is redundant
 2024-11-16 16:57:32 -08:00
Nuno Campos 84ef939bf4 sdk-js 0.0.24 2024-11-14 18:17:22 -08:00
Nuno Campos bdc22ea127 sdk-js: Accept command when creating run 2024-11-14 18:17:04 -08:00
Nuno Campos 4cc6d789ed Fix stream_mode=messages used together with subgraphs=True 2024-10-30 19:35:28 -07:00
Nuno Campos 05f008cbfb Lint 2024-10-23 20:30:32 -07:00
Nuno Campos a8ae2a52a3 Lint 2024-10-23 20:27:18 -07:00
Nuno Campos aa245a8e71 Fix up 2024-10-23 20:22:04 -07:00
Nuno Campos 7fba675e8a sdk-py: Add arg to get history for subgraphs 2024-09-29 19:28:52 -07:00
Nuno Campos 47fe321e31 Lint 2024-09-22 12:51:06 -07:00
Nuno Campos 1f347ed48e perf: Intern string constants 2024-09-22 12:45:47 -07:00
Nuno Campos d6015e7bf9 Remove runtime value substitution 
- doesn't work as expected
 2024-09-22 12:44:48 -07:00
Nuno Campos 84a45d186c Fix 2024-09-22 12:42:34 -07:00
Nuno Campos e76f49c7f0 Fix flaky test 2024-09-22 12:37:24 -07:00
Nuno Campos 74f34db9e4 Fix sync kafka 2024-09-22 12:04:43 -07:00
Nuno Campos 644f14991e Fix kfka 2024-09-22 12:04:17 -07:00
Nuno Campos 81a9a2f903 Use a different strategy, add test 2024-09-21 18:48:23 -07:00
Nuno Campos 2fccd09585 Fix 2024-09-21 17:52:17 -07:00
Nuno Campos 89bb7fe178 Skip test for now 2024-09-21 17:47:36 -07:00
Nuno Campos beeb2aa8ba Detect multiple subgraphs in single node 2024-09-21 17:44:11 -07:00
Nuno Campos 30b631aaff Rewrite imports 2024-09-21 17:41:05 -07:00
Nuno Campos d9854b36eb Move to langgraph.types 2024-09-21 17:37:17 -07:00
Nuno Campos 3cbd70ffc9 Fix docs 2024-09-21 17:30:04 -07:00
Nuno Campos 313e3eed3e Fix circular import 2024-09-21 17:26:29 -07:00
Nuno Campos 9f8d71c65b Lint 2024-09-21 17:23:12 -07:00
Nuno Campos 89fb8d506f Add more comments and docstrings 2024-09-21 17:21:18 -07:00
Nuno CamposandGitHub e40aabb1c1 Update retry.py 2024-09-18 10:36:40 -07:00
Nuno CamposandGitHub 0bfeb7f4e1 Update types.py 2024-09-18 10:24:28 -07:00
Nuno CamposandGitHub fd0b52f4ff Update retry.py 2024-09-18 10:23:52 -07:00
Nuno CamposandNuno Campos 4793b3f5e1 Use a lock for all operations on sqlite checkpointer 
- Otherwise when used in multiple subgraphs in parallel separate queries can interfere w each other
 2024-09-03 09:20:17 -07:00
Nuno CamposandNuno Campos 3c5913aa29 Remove pydantic base class from Pregel/PregelNode 2024-09-03 09:20:17 -07:00
Nuno Campos af666a87fb sqlite 1.0.2 2024-09-02 17:58:01 -07:00
Nuno Campos 6e9f54e5ae postgres 1.0.6 2024-09-02 17:57:55 -07:00
Nuno Campos dd4a15b569 Require latest version of langgraph-checkpoint 2024-09-02 17:57:33 -07:00
Nuno Campos 3b2a237deb Lint 2024-09-02 17:45:57 -07:00
Nuno Campos 0cc3799298 checkpoint: Implement sync methods in async checkpointers 
- These are needed when subgraphs are invoked synchronously in nodes
 2024-09-02 17:43:34 -07:00
Nuno Campos ddeb9d7314 Disable test in old versions of py 2024-09-02 17:42:37 -07:00
Nuno Campos d65d0ec665 test: Ensure that async checkpointers in tests are setup in same event loop as they are used in 
- This more closely remembers the environment they're used in, so it's what we should be testing
- Remove unnecessary pytest-asyncio dependency, use anyio pytest plugin instead
- Convert remaining async tests using only memory checkpointer to use all existing ones
 2024-09-02 17:24:54 -07:00
Nuno CamposandNuno Campos 8154ab784e For input checkpoint use filtered input writes in checkpoint metadata 
- if we use the raw input we can end up saving keys that were actually ignored (because not one of the input keys), which is incosistent
 2024-08-30 13:24:41 -07:00
Nuno Campos 03785c7d83 sdk: Add on_completion param 2024-08-24 21:34:35 -07:00