# \#feature-request **URL:** https://forum.langchain.com/tag/feature-request/15.md [Latest](https://forum.langchain.com/latest.md) · [Categories](https://forum.langchain.com/categories.md) · [Tags](https://forum.langchain.com/tags.md) --- ## [Proposal: checkpoint aware context management for long-running agents (+ optional KV-cache editing)](https://forum.langchain.com/t/proposal-checkpoint-aware-context-management-for-long-running-agents-optional-kv-cache-editing/4792)
**Author:** [@Anipaleja](https://forum.langchain.com/u/Anipaleja)\ **Replies:** 4\ **Last updated:** [October 29, 2026, 1:46am UTC](https://forum.langchain.com/t/proposal-checkpoint-aware-context-management-for-long-running-agents-optional-kv-cache-editing/4792 "2026-10-29T01:46:03Z")
Hi maintainers, Ive been working on a context management layer for LangGraph and wanted to get some feedback before opening a PR. LangGraph already has tools like pre\_model\_hook, RemoveMessage, and trim\_messages, but I … --- ## [Production use of PostgresSaver: service-owned migrations and checkpoint retention in Node.js](https://forum.langchain.com/t/production-use-of-postgressaver-service-owned-migrations-and-checkpoint-retention-in-node-js/4481)
**Author:** [@waiz-ksolves](https://forum.langchain.com/u/waiz-ksolves)\ **Replies:** 3\ **Last updated:** [October 28, 2026, 6:38pm UTC](https://forum.langchain.com/t/production-use-of-postgressaver-service-owned-migrations-and-checkpoint-retention-in-node-js/4481 "2026-10-28T18:38:50Z")
We are planning to use @langchain/langgraph-checkpoint-postgres in a production Node.js service and have a few questions about the recommended database ownership and retention model. Our service team normally owns all P… --- ## [Proposal: provider-neutral typed decisions for LangGraph Python and JS](https://forum.langchain.com/t/proposal-provider-neutral-typed-decisions-for-langgraph-python-and-js/4936)
**Author:** [@sjungwon03](https://forum.langchain.com/u/sjungwon03)\ **Replies:** 0\ **Last updated:** [October 28, 2026, 5:04pm UTC](https://forum.langchain.com/t/proposal-provider-neutral-typed-decisions-for-langgraph-python-and-js/4936 "2026-10-28T17:04:01Z")
I’d like to connect dedicated decision models to existing LangGraph LLM workflows in both Python and JS. A decision should be able to request any subset of named Choice, Noul, and Score judgments, then use the result eit… --- ## [Feature Request: Add a pluggable binary classification evaluator for System 1 models](https://forum.langchain.com/t/feature-request-add-a-pluggable-binary-classification-evaluator-for-system-1-models/4934)
**Author:** [@Aditya1812](https://forum.langchain.com/u/Aditya1812)\ **Replies:** 0\ **Last updated:** [October 28, 2026, 4:08pm UTC](https://forum.langchain.com/t/feature-request-add-a-pluggable-binary-classification-evaluator-for-system-1-models/4934 "2026-10-28T16:08:19Z")
Description I would like to propose adding a lightweight binary classification evaluator to OpenEvals. Many evaluation workflows today use LLM-as-a-judge, where a larger model performs a more deliberative, rubric-based … --- ## [Feature Proposal: First-Class AgentRouter and LLMRouter Abstractions](https://forum.langchain.com/t/feature-proposal-first-class-agentrouter-and-llmrouter-abstractions/4915)
**Author:** [@yogeshkulkarni11](https://forum.langchain.com/u/yogeshkulkarni11)\ **Replies:** 0\ **Last updated:** [October 27, 2026, 5:00pm UTC](https://forum.langchain.com/t/feature-proposal-first-class-agentrouter-and-llmrouter-abstractions/4915 "2026-10-27T17:00:34Z")
Feature Proposal: First-Class AgentRouter and LLMRouter Abstractions Background LangGraph provides excellent low-level primitives for building agent workflows, including nodes, edges, conditional routing, Command, state … --- ## [There is no way to use custom filters like \`@\>\` with \`PGVectorStore\`](https://forum.langchain.com/t/there-is-no-way-to-use-custom-filters-like-with-pgvectorstore/4594)
**Author:** [@wbyoung](https://forum.langchain.com/u/wbyoung)\ **Replies:** 2\ **Last updated:** [October 27, 2026, 4:31pm UTC](https://forum.langchain.com/t/there-is-no-way-to-use-custom-filters-like-with-pgvectorstore/4594 "2026-10-27T16:31:45Z")
It appears that it would be easy to subclass PGVectorStore and add support for custom operations via the filters if the buildFilterClauses method were not private. I’m new to the community. Is this the right place to di… --- ## [Proposal: additional docs for implementing custom DB checkpointers or a guide on generic base checkpointer](https://forum.langchain.com/t/proposal-additional-docs-for-implementing-custom-db-checkpointers-or-a-guide-on-generic-base-checkpointer/3735)
**Author:** [@Wonder-donbury](https://forum.langchain.com/u/Wonder-donbury)\ **Replies:** 3\ **Last updated:** [October 23, 2026, 6:58pm UTC](https://forum.langchain.com/t/proposal-additional-docs-for-implementing-custom-db-checkpointers-or-a-guide-on-generic-base-checkpointer/3735 "2026-10-23T18:58:26Z")
Currently I’m guessing a lot of agent PoC made with LangGraph is preparing to get to production level, and so is my project, and some projects that needs to be deployed on-prem, database licensing of the client’s side is… --- ## [Question on Open Github Issue #7345: Status of configurable PostgreSQL schema](https://forum.langchain.com/t/question-on-open-github-issue-7345-status-of-configurable-postgresql-schema/4558)
**Author:** [@alive](https://forum.langchain.com/u/alive)\ **Replies:** 1\ **Last updated:** [September 18, 2026, 2:28pm UTC](https://forum.langchain.com/t/question-on-open-github-issue-7345-status-of-configurable-postgresql-schema/4558 "2026-09-18T14:28:22Z")
Hey everyone! :waving\_hand: Quick question regarding Issue #7345 (“Configurable PostgreSQL schema for langgraph-checkpoint-postgres”): https://github.com/langchain-ai/langgraph/issues/7345 It looks like there has been… --- ## [How are you handling governance for production LangChain agents? (PII, cost caps, tool safety)](https://forum.langchain.com/t/how-are-you-handling-governance-for-production-langchain-agents-pii-cost-caps-tool-safety/4315)
**Author:** [@nagasatish](https://forum.langchain.com/u/nagasatish)\ **Replies:** 5\ **Last updated:** [September 10, 2026, 11:21am UTC](https://forum.langchain.com/t/how-are-you-handling-governance-for-production-langchain-agents-pii-cost-caps-tool-safety/4315 "2026-09-10T11:21:19Z")
Curious how others are approaching governance for LangChain agents in production — specifically: PII leaking through RAG pipelines When a retriever pulls documents containing customer data (SSNs, emails, credit cards)… --- ## [Feature request: let a add\_conditional\_edges branch write into an existing add\_edge(\[...\], dest) barrier](https://forum.langchain.com/t/feature-request-let-a-add-conditional-edges-branch-write-into-an-existing-add-edge-dest-barrier/4513)
**Author:** [@AlejandroTorresMunoz](https://forum.langchain.com/u/AlejandroTorresMunoz)\ **Replies:** 0\ **Last updated:** [September 9, 2026, 9:11am UTC](https://forum.langchain.com/t/feature-request-let-a-add-conditional-edges-branch-write-into-an-existing-add-edge-dest-barrier/4513 "2026-09-09T09:11:36Z")
The gap add\_edge(\[source1, source2, ...\], dest) creates a NamedBarrierValue channel: dest becomes a real AND-join, firing only once every named source has written to it since it last fired. This works great, as long as e… --- ## [Structured query over withheld large tool results — a lossless alternative to clearing/summarizing](https://forum.langchain.com/t/structured-query-over-withheld-large-tool-results-a-lossless-alternative-to-clearing-summarizing/4497)
**Author:** [@shex1627](https://forum.langchain.com/u/shex1627)\ **Replies:** 0\ **Last updated:** [September 6, 2026, 7:16am UTC](https://forum.langchain.com/t/structured-query-over-withheld-large-tool-results-a-lossless-alternative-to-clearing-summarizing/4497 "2026-09-06T07:16:15Z")
I’ve been writing react agents and MCP servers for a while now, and a recurring problem is that MCP tool output is often large JSON — which gets expensive in tokens fast. As far as I’ve found, LangChain has two ways to h… --- ## [Feature Request: Dgraph Integration for LangGraph](https://forum.langchain.com/t/feature-request-dgraph-integration-for-langgraph/4477)
**Author:** [@LakshimiRam-073](https://forum.langchain.com/u/LakshimiRam-073)\ **Replies:** 0\ **Last updated:** [September 2, 2026, 5:31pm UTC](https://forum.langchain.com/t/feature-request-dgraph-integration-for-langgraph/4477 "2026-09-02T17:31:50Z")
We are evaluating Dgraph as a graph database for our GraphRAG use case and would like to have a native Dgraph integration/client in LangGraph, similar to the existing Neo4j integration. The integration would ideally sup… --- ## [A checkpointer that accepts two concurrent writers still scores conformance\_level = FULL](https://forum.langchain.com/t/a-checkpointer-that-accepts-two-concurrent-writers-still-scores-conformance-level-full/4460)
**Author:** [@bharatnpti](https://forum.langchain.com/u/bharatnpti)\ **Replies:** 1\ **Last updated:** [September 2, 2026, 9:43am UTC](https://forum.langchain.com/t/a-checkpointer-that-accepts-two-concurrent-writers-still-scores-conformance-level-full/4460 "2026-09-02T09:43:25Z")
I ran the checkpoint-conformance suite from main against three savers: InMemorySaver AsyncPostgresSaver 3.1.2 one I wrote that deliberately accepts writes from any number of workers on the same thread All three pass. … --- ## [Proposal - Targeted Refactoring For Cognitive Complexity in Core Modules](https://forum.langchain.com/t/proposal-targeted-refactoring-for-cognitive-complexity-in-core-modules/4441)
**Author:** [@ivi4lang](https://forum.langchain.com/u/ivi4lang)\ **Replies:** 0\ **Last updated:** [August 26, 2026, 3:03am UTC](https://forum.langchain.com/t/proposal-targeted-refactoring-for-cognitive-complexity-in-core-modules/4441 "2026-08-26T03:03:45Z")
Hi all, While doing a code ‘onboarding’, I ran a local SQ scan that flagged some areas for high cognitive complexity. One example would be \_merge\_splits()\`in\`langchain\_text\_splitters/base.py\`. See the image below. T… --- ## [Please don't depreciate Turns View](https://forum.langchain.com/t/please-dont-depreciate-turns-view/4397)
**Author:** [@Digimox](https://forum.langchain.com/u/Digimox)\ **Replies:** 0\ **Last updated:** [August 21, 2026, 9:25am UTC](https://forum.langchain.com/t/please-dont-depreciate-turns-view/4397 "2026-08-21T09:25:16Z")
I use Turns View all the time, please don’t deprecate it. When this was launched it was a massive help. The Messages view doesn’t work for me because it has far too much detail. Thanks --- ## [Proposal: Add Feedback as a Standard Resource on the Langgraph API Server](https://forum.langchain.com/t/proposal-add-feedback-as-a-standard-resource-on-the-langgraph-api-server/4355)
**Author:** [@paychex-ssmithrand](https://forum.langchain.com/u/paychex-ssmithrand)\ **Replies:** 1\ **Last updated:** [August 18, 2026, 6:08pm UTC](https://forum.langchain.com/t/proposal-add-feedback-as-a-standard-resource-on-the-langgraph-api-server/4355 "2026-08-18T18:08:18Z")
Hello, I’d like to bring a proposal forward that would create a /feedback route and accompanying Resource definitions to the Langgraph API Server. There exists a pre-signed url flow for something like this today, howev… --- ## [Adding an end-to-end example: from locally-served model to agentic flow orchestration](https://forum.langchain.com/t/adding-an-end-to-end-example-from-locally-served-model-to-agentic-flow-orchestration/4132)
**Author:** [@cheehook](https://forum.langchain.com/u/cheehook)\ **Replies:** 5\ **Last updated:** [August 14, 2026, 6:08am UTC](https://forum.langchain.com/t/adding-an-end-to-end-example-from-locally-served-model-to-agentic-flow-orchestration/4132 "2026-08-14T06:08:06Z")
Hi community, Speaking as an agentic-application developer myself: I keep meeting people who want to adopt LangGraph with their own self-served local models and custom services, and they can’t see how the layers relate.… --- ## [Proposal: add safe keep\_latest pruning to PostgresSaver](https://forum.langchain.com/t/proposal-add-safe-keep-latest-pruning-to-postgressaver/4291)
**Author:** [@wangjiawei-vegetable](https://forum.langchain.com/u/wangjiawei-vegetable)\ **Replies:** 2\ **Last updated:** [August 7, 2026, 2:39am UTC](https://forum.langchain.com/t/proposal-add-safe-keep-latest-pruning-to-postgressaver/4291 "2026-08-07T02:39:00Z")
Hi maintainers, I would like to propose implementing the existing checkpoint prune interface for PostgresSaver and AsyncPostgresSaver. For an initial contribution, I propose supporting safe pruning for ordinary checkpo… --- ## [Type annotation on stream\_event v3?](https://forum.langchain.com/t/type-annotation-on-stream-event-v3/4196)
**Author:** [@dhnam](https://forum.langchain.com/u/dhnam)\ **Replies:** 6\ **Last updated:** [July 31, 2026, 1:01pm UTC](https://forum.langchain.com/t/type-annotation-on-stream-event-v3/4196 "2026-07-31T13:01:37Z")
Recently, Langgraph has v3 on stream\_event and astream\_event. I tried using it, but I found it doesn’t have any type annotation - and things get worse when I try to annotate it with (Async)GraphRunStream, as it dynamica… --- ## [Implement or declare extended capabilities in BaseCheckpointSaver](https://forum.langchain.com/t/implement-or-declare-extended-capabilities-in-basecheckpointsaver/4264)
**Author:** [@eddienubes](https://forum.langchain.com/u/eddienubes)\ **Replies:** 2\ **Last updated:** [July 30, 2026, 10:52am UTC](https://forum.langchain.com/t/implement-or-declare-extended-capabilities-in-basecheckpointsaver/4264 "2026-07-30T10:52:15Z")
Hi guys! I’ve been looking for a documented way to copy a thread and stumbled across the documented “extended capabilities” to: adelete\_for\_runs acopy\_thread aprune aget\_delta\_channel\_history at Checkpointers - Docs … --- ## [Improve. the definition structure](https://forum.langchain.com/t/improve-the-definition-structure/4222)
**Author:** [@SheikhAriful](https://forum.langchain.com/u/SheikhAriful)\ **Replies:** 3\ **Last updated:** [July 22, 2026, 11:04pm UTC](https://forum.langchain.com/t/improve-the-definition-structure/4222 "2026-07-22T23:04:52Z")
I think LangChain should improve its tool definition structure, like the Vercel AI SDK. This structure is cleaner and JavaScript-friendly. example: \`\`\`const weatherTool = tool({ name: “get weather”, description: ‘Get… --- ## [Feedback requested: evaluating commit-time action validity in LangGraph workflows](https://forum.langchain.com/t/feedback-requested-evaluating-commit-time-action-validity-in-langgraph-workflows/4178)
**Author:** [@Nixalp](https://forum.langchain.com/u/Nixalp)\ **Replies:** 8\ **Last updated:** [July 22, 2026, 5:43pm UTC](https://forum.langchain.com/t/feedback-requested-evaluating-commit-time-action-validity-in-langgraph-workflows/4178 "2026-07-22T17:43:45Z")
I am exploring a LangGraph adapter for CAV-Bench, an open-source deterministic benchmark for evaluating whether tool-using agent actions remain valid when they commit. The benchmark focuses on failure patterns that fina… --- ## [Feature Request: Support OpenAI GPT-5.6 Explicit Prompt Cache Breakpoints in @langchain/openai](https://forum.langchain.com/t/feature-request-support-openai-gpt-5-6-explicit-prompt-cache-breakpoints-in-langchain-openai/4200)
**Author:** [@KurtzOmer](https://forum.langchain.com/u/KurtzOmer)\ **Replies:** 3\ **Last updated:** [July 22, 2026, 12:53pm UTC](https://forum.langchain.com/t/feature-request-support-openai-gpt-5-6-explicit-prompt-cache-breakpoints-in-langchain-openai/4200 "2026-07-22T12:53:30Z")
Feature Request: Support OpenAI GPT-5.6 Explicit Prompt Cache Breakpoints in @langchain/openai Summary OpenAI GPT-5.6 introduces explicit prompt cache breakpoints, allowing applications to precisely control which parts o… --- ## [Add native Document Reranking support to langchain-openrouter](https://forum.langchain.com/t/add-native-document-reranking-support-to-langchain-openrouter/4185)
**Author:** [@Umar4880](https://forum.langchain.com/u/Umar4880)\ **Replies:** 4\ **Last updated:** [July 22, 2026, 12:08pm UTC](https://forum.langchain.com/t/add-native-document-reranking-support-to-langchain-openrouter/4185 "2026-07-22T12:08:08Z")
Proposing Native Document Reranking Support for langchain-openrouter Target Namespace: libs/partners/openrouter Base Interface Class: langchain\_core.documents.BaseDocumentCompressor Use Case OpenRouter natively support… --- ## [Bypassing Langgraph SuperSteps with Sub-graph](https://forum.langchain.com/t/bypassing-langgraph-supersteps-with-sub-graph/4046)
**Author:** [@albertchristianto](https://forum.langchain.com/u/albertchristianto)\ **Replies:** 5\ **Last updated:** [June 28, 2026, 9:02am UTC](https://forum.langchain.com/t/bypassing-langgraph-supersteps-with-sub-graph/4046 "2026-06-28T09:02:15Z")
I am currently building a graph orchestration and execution platform using LangGraph as the backend. I’m trying to optimize the execution time of a graph by bypassing LangGraph’s superstep execution model. One approach … --- ## [About LangGraph distribution model and enterprises](https://forum.langchain.com/t/about-langgraph-distribution-model-and-enterprises/4019)
**Author:** [@leo-gan](https://forum.langchain.com/u/leo-gan)\ **Replies:** 7\ **Last updated:** [June 26, 2026, 7:12pm UTC](https://forum.langchain.com/t/about-langgraph-distribution-model-and-enterprises/4019 "2026-06-26T19:12:10Z")
LangGraph needs a distribution model, not just a runtime LangGraph executes graphs well. What it can’t do is let teams share them without copy-paste, fragile cross-repo imports, or ad-hoc HTTP calls with no contract. T… --- ## [LangGraph orchestration Problem](https://forum.langchain.com/t/langgraph-orchestration-problem/4017)
**Author:** [@akin](https://forum.langchain.com/u/akin)\ **Replies:** 5\ **Last updated:** [June 24, 2026, 9:00am UTC](https://forum.langchain.com/t/langgraph-orchestration-problem/4017 "2026-06-24T09:00:30Z")
Guys, I have a problem. I’m building an orchestration layer, and the agent—for example—asks the user for a keyword, extracts the keyword, but it also calls the Excel tool and writes the data to Excel. The user didn’t ask… --- ## [Langchain model providing adapters](https://forum.langchain.com/t/langchain-model-providing-adapters/3978)
**Author:** [@daya\_2k](https://forum.langchain.com/u/daya_2k)\ **Replies:** 2\ **Last updated:** [June 22, 2026, 3:28pm UTC](https://forum.langchain.com/t/langchain-model-providing-adapters/3978 "2026-06-22T15:28:36Z")
Hi team, I have been using langchain since it has been released. We have bunch of adapters {ChatBedrock, ChatGoogleGenerativeAI..} to integrate an LLM for langchain powered AI app development. However, some firms are u… --- ## [LangGraph thread copy can take 12+ minutes: recommended production pattern?](https://forum.langchain.com/t/langgraph-thread-copy-can-take-12-minutes-recommended-production-pattern/3763)
**Author:** [@gouveags](https://forum.langchain.com/u/gouveags)\ **Replies:** 3\ **Last updated:** [June 15, 2026, 1:34pm UTC](https://forum.langchain.com/t/langgraph-thread-copy-can-take-12-minutes-recommended-production-pattern/3763 "2026-06-15T13:34:14Z")
Hi LangGraph team, I opened a GitHub issue here with the full details: Thread copy endpoint can take 12+ minutes with no async/progress or shallow-copy option · Issue #7859 · langchain-ai/langgraph · GitHub We use Lang… --- ## [Proposal: a small local helper for readable run traces via PR](https://forum.langchain.com/t/proposal-a-small-local-helper-for-readable-run-traces-via-pr/3878)
**Author:** [@Devansh-Ruia](https://forum.langchain.com/u/Devansh-Ruia)\ **Replies:** 1\ **Last updated:** [June 6, 2026, 9:52pm UTC](https://forum.langchain.com/t/proposal-a-small-local-helper-for-readable-run-traces-via-pr/3878 "2026-06-06T21:52:39Z")
Debugging a LangGraph run locally is still noisy. When something goes wrong I usually end up either printing raw stream\_mode="debug" chunks and squinting at them, or reaching for LangSmith. For small/medium graphs that f… [Next page](https://forum.langchain.com/tag/feature-request/15.md?match_all_tags=true&page=1&tags%5B%5D=feature-request)