As companies scale, the technology supporting operations can become a liability just as quickly as it becomes an asset. Disconnected systems, site-specific tools, spreadsheets, and manual workarounds can create data silos that make it harder to spot problems early, coordinate responses, and make decisions with confidence. For Jabil, a global manufacturing company with more than…
Article URL: https://trellner.com/reports/manufactured-sources-behind-ai-recommendations/ Comments URL: https://news.ycombinator.com/item?id=49536375 Points: 240 # Comments: 110
Hugging Face Blog published: Real-Time Intelligence with IBM Time Series Models on Confluent
Article URL: https://lwn.net/Articles/1090585/ Comments URL: https://news.ycombinator.com/item?id=49535752 Points: 233 # Comments: 38
We believe the future is a multi-model, multi-harness world. And we think it needs a new trust model. In 1988, Norm Hardy described a problem that had been quietly breaking systems for years: the confused deputy. A program that takes action using its permissions instead of yours. Today, every AI agent is that deputy. It...
Learn how Docker Sandboxes can make AI evaluation workflows more reproducible with consistent execution, structured artifacts, and runtime evidence.
Play music from files, iCloud & streams across Apple devices Discussion | Link
Build forms into your product with your coding agent Discussion | Link
ATV Big Air Tour uses ChatGPT Work to speed up marketing, merchandising, and more. It even turned merchandise photos into an inventory website in 15 minutes.
In the previous post , we introduced KubeVirtBMC and showed how it provides virtual BMC endpoints for KubeVirt VMs. We tested it with raw IPMI and Redfish commands. That was fun, but the real power of...
Turn any prompt into a brick set you can actually build Discussion | Link
Fable 5.1 is out, and the hated Fable data retention policy is not just being altered, but entirely removed in the meantime. Plus, why increased caching is a win-win.
Referendum result means fewer seats in parliament and new rules on candidates, ahead of December elections Guinea-Bissau voters have approved a new constitution, which critics say will undermine democracy, that significantly expands presidential powers ahead of elections due in December. According to provisional results, 70% of voters approved sweeping changes in the tiny west African state’s first constitutional amendment since revisions that ended the one-party socialist state more than three decades ago. Continue reading...
“Why are you taking this class?” That seems like a fair question. After tenth grade or so, it’s a choice, after all. One honest answer is, “I have to get a good grade to get to where I want to go.” That means certification, compliance, regurgitation. It means enrollment in the outcome, not the process. […]
Police are investigating the explosion of an unidentified object at a train station in southern Germany. Meanwhile, a malfunction at a German power station near Cologne is being probed as a deliberate act. More on DW.
No date has been set for the all-British heavyweight boxing showdown, but it is expected to be held in November.
Design with AI agents - live on the same canvas Discussion | Link
An Iranian fisherwoman explains how her idyllic seaside life was shattered when the US and Israel began their bombing.
The U.S. military hit targets in Iran on Tuesday and Tehran fired missiles and drones at various sites across the region in response as hostilities flare once again in an intermittent war.
Study reveals that pesticide poisoning kills 11,000 people each year, with India accounting for nearly 60% of fatalities Almost half of the world’s farmers are poisoned by pesticides every single year, a study has found. Using publicly available data from 2006-2023, the study, which was commissioned by Pesticide Action Network , found there to be an estimated 402-433m cases of unintentional acute pesticide poisoning of farmers and farm workers every year. Continue reading...
Sergei Loznitsa likens removal of €2m grant to ‘a punishment in kindergarten’ on eve of Venice film festival One of Ukraine’s most acclaimed film-makers has criticised the European Commission’s decision to cut off funds to the Venice Biennale over the opening of Russia’s pavilion, likening it to “a punishment in kindergarten”. The Biennale drew heavy criticism this spring when it allowed Russia to use its pavilion for the first time since 2022, despite the ongoing full-scale invasion of Ukraine. Continue reading...
iRobot has announced a new flagship robot vacuum, which it will showcase at IFA in Berlin this week, the company's first big tech trade show in years. The Roomba maker will be exhibiting under its new owner, Picea Robotics, the contract manufacturer that purchased the once-troubled American robotics company out of bankruptcy in January. The […]
Direct2D has always been the biggest hurdle for Paint.NET on WINE, and it's clear that it will never be completed enough for Paint.NET's use. And I can't just "disable" the use of Direct2D. So, instead, Paint.NET now has an internal, from-scratch, clean-room reverse-engineered rewrite of Direct2D that it uses on WINE (triggered by using /wine ). It lives in PaintDotNet.Windows.Direct2D1.Managed.dll . This was written by our good friend Claude , without whom this would NOT have been possible and would NEVER have happened. [...] Most of this code is, as they say, "vibe coded." By that I mean that it has not been thoroughly reviewed, it's more "trust me bro" style. I cannot possibly review 180,000 lines of code, it's just way way way too much. For reference, the rest of Paint.NET is about 700,000 lines of code and I've been working on it for over 20 years. [...] At times, Claude was working with the fury of 10 freshly unshackled Einstein genius-level 10x coders. And other times ... well, not so much. I had to babysit Claude quite a bit to make sure it did resource management correctly (for awhile it just wasn't doing the COM equivalent of AddRef() for reference counted objects, oops). I had to slap it a few times when I found some really bad design or architecture decisions. And I was also impressed at some rather clever and tireless reverse engineering work it did to figure out all the formulas needed for implementing Direct2D's built-in effects library. — Rick Brewster , author of Paint.NET Tags: reverse-engineering , coding-agents , claude , generative-ai , ai , llms , dotnet , linux , vibe-coding
Initial release release(langchain): 1.4.0a4 test(langchain): cover mixed-era ClientGroup and group elicitation Update libs/langchain_v1/langchain/mcp/adapter.py fix(langchain): drive MCP elicitation via member session for fastmcp 4.0.1 fix(sdk): use latest fastmcp and rm reentrant impl cr cr refactor(langchain): inline MCP client arming into __init__ refactor(langchain): stamp an arm marker instead of introspecting the handler closure fix(langchain): gate MCP interrupt routing on the negotiated protocol era refactor(langchain): drop MCP elicitation flag, derive interrupt routing from the client fix(sdk): add _ReentrantClientGroup fix(langchain): narrow MCPAdapter.client union in mcp tests for mypy chore(langchain): format mcp/adapter.py release(langchain): 1.4.0a3 feat(langchain): group MCP tool metadata under an mcp namespace refactor(langchain): stop exporting MCPAdapterTarget from langchain.mcp refactor(langchain): rename convert_mcp_tool_to_langchain_tool to as_langchain_tool refactor(langchain): rename MCPAdapter.get_tools to list_tools feat(langchain): expose cache_mode on MCPAdapter.get_tools chore(langchain): require fastmcp 4.0.0 feat(langchain): accept a ClientGroup as an MCPAdapter target feat(langchain): mark the langchain.mcp namespace as beta Revert "feat(langchain): accept a ClientGroup as an MCPAdapter target" feat(langchain): accept a ClientGroup as an MCPAdapter target chore(langchain): require fastmcp 4.0.0b5 fix(langchain): require a str MCP target to be an http(s) URL release(langchain): 1.4.0a2 fix(langchain): require full fastmcp for the mcp extra fix(langchain): name the content type MCP conversion could not handle release(langchain): 1.4.0a1 test(langchain): skip MCP tests on a pydantic older than mcp supports test(langchain): drive MCP tests through FastMCP's own utilities fix(langchain/mcp): review edits ( #39974 ) Merge remote-tracking branch 'origin/master' into sydney-runkle/langchain/simplify-mcp-adapter fix(langchain): import assert_never from typing_extensions test(langchain): fix type errors in the MCP test suite test(langchain): cover protocol eras across a multi-server fleet test(langchain): cover both MCP protocol eras through one adapter refactor(langchain): one elicitation request type per mode refactor(langchain): keep the elicitation types out of langchain.mcp fix(langchain): make the two FastMCP-private dependencies fail loudly refactor(langchain): one elicitation response type per action refactor(langchain): refuse MCP continuation rounds instead of polling release(langchain): 1.3.18 ( #39966 ) refactor(langchain): tighten the elicitation answer types refactor(langchain): move _declare_elicitation_capability to elicitation docs(langchain): trim the langchain.mcp docstrings fix(langchain): bound the MCP input-required retry loop refactor(langchain): trim the MCPAdapterTarget docs refactor(langchain): use ELICITATION_INTERRUPT_TYPE as the discriminator refactor(langchain): drop MCPAdapter.aclose fix(langchain): preserve content-block shape in PIIMiddleware redaction ( #39894 ) fix(core): shore up indexing in genai v1 streaming content ( #39964 ) fix(langchain): guard MCP elicitation calls against a dying session feat(langchain): answer MCP elicitation with a LangGraph interrupt feat(langchain): port MCP tool conversion from langchain-mcp-adapters feat(langchain): drop elicitation from MCPAdapter chore(langchain): require FastMCP 4.0.0b4 for the mcp extra feat(langchain): simplify MCPAdapter construction feat(langchain): langchain.mcp namespace, MCPAdapter release(langchain): 1.3.17 ( #39893 ) fix(langchain): frame custom HITL rejection reasons ( #39773 ) chore(deps): bump minor and patch dependencies ( #39869 ) release(langchain): 1.3.16 ( #39806 ) feat(core): add standard model exception types ( #39538 ) feat(langchain): support custom token_counter in ContextEditingMiddleware ( #39754 ) fix(langchain): re-raise non-retryable exceptions in ModelRetryMiddleware ( #38960 ) chore(langchain): update docs on error handling for json schema ( #39632 ) fix(langchain): preserve final repeated schema ordering ( #39284 ) release(langchain): 1.3.15 ( #39595 ) feat(langchain): expose trace_policy on AgentMiddleware ( #38910 ) chore(langchain): fix type errors in tests ( #39589 ) chore: bump h2 from 4.3.0 to 4.4.1 in /libs/langchain_v1 ( #39324 ) fix(langchain): preserve history on SummarizationMiddleware summary failure ( #39268 ) fix(langchain): handle import error in LLMToolEmulator by model ( #39290 ) refactor(langchain): update doc strings ( #39305 ) feat(langchain): add state_schema param to wrap_tool_call ( #39292 ) fix(langchain): re-export PIIMatch from middleware package ( #39291 ) fix(langchain): restrict narrowed ToolStrategy in bound tools ( #39259 ) feat(langchain): filter internal middleware model calls from messages projection ( #39252 ) chore: bump aiohttp from 3.14.1 to 3.14.3 in /libs/langchain_v1 ( #39242 ) chore: bump cryptography from 48.0.1 to 50.0.0 in /libs/langchain_v1 ( #39240 ) test(langchain): regression test for shell tool + checkpointer msgpack error ( #39267 ) fix(langchain): handle malformed structured-output responses ( #39245 ) fix(langchain): prevent orphaned tool_calls in ToolCallLimitMiddleware end behavior ( #39258 ) fix(langchain): add aliases for bedrock mantle chat models ( #39260 ) feat(langchain): add LangSmith provider to init_chat_model ( #39224 ) fix(langchain): clear stale structured_response between checkpointed turns ( #39248 ) fix(langchain): stop HITL approval gates from silently failing open ( #39247 ) chore: bump the minor-and-patch group across 3 directories with 7 updates ( #39187 ) fix(langchain): propagate model middleware control flow ( #39199 ) fix(langchain): update Anthropic config test ( #39172 ) chore: bump pyasn1 from 0.6.3 to 0.6.4 in /libs/langchain_v1 ( #39026 ) chore: bump pillow from 12.2.0 to 12.3.0 in /libs/langchain_v1 ( #38994 ) feat(core): add reasoning_effort as a standard chat model parameter ( #38887 ) docs(langchain): clarify ToolRetryMiddleware exception handling ( #38884 ) release(langchain): 1.3.14 ( #38883 ) fix(langchain): only retry retryable exceptions in ToolRetryMiddleware ( #38845 ) feat(langchain): ToolErrorMiddleware ( #38781 ) release(langchain): 1.3.13 ( #38787 ) feat(langchain): add meta extra and support langchain-meta in init_chat_model ( #38786 ) feat(openai): support explicit prompt caching ( #38762 ) chore(deps): refresh lockfiles ( #38746 ) release(langchain): 1.3.12 ( #38730 ) fix(langchain): propagate interrupts through ToolRetryMiddleware ( #38722 ) fix(langchain): avoid shared process-group kill in shell middleware ( #36359 ) fix(langchain): sanitize anthropic cache markers on fallback retries ( #37867 ) style: fix some ruff preview rules in langchain_v1 and standard-tests ( #38657 ) chore(langchain): add types in agent middleware tests ( #38188 ) release(langchain): 1.3.11 ( #38377 ) fix(langchain,openai): only set strict=True on tools for OpenAI-compatible models in ProviderStrategy ( #38370 ) chore: bump pydantic-settings from 2.12.0 to 2.14.2 in /libs/langchain_v1 ( #38279 ) chore: bump vcrpy from 8.1.1 to 8.2.1 in /libs/langchain_v1 ( #38280 ) chore: bump langsmith from 0.8.9 to 0.8.18 in /libs/langchain_v1 ( #38281 ) docs(langchain): document summarization prompt contract ( #38256 ) release(langchain): 1.3.10 ( #38255 ) chore: bump cryptography from 46.0.7 to 48.0.1 in /libs/langchain_v1 ( #38176 ) chore: bump aiohttp from 3.14.0 to 3.14.1 in /libs/langchain_v1 ( #38179 ) fix(langchain): switch summary format ( #38171 ) fix(langchain): detect provider strategy for dated gpt-5.2 / gpt-5.4 snapshots ( #38222 ) chore(langchain): improve typing in tests ( #38163 ) chore: bump pyjwt from 2.12.0 to 2.13.0 in /libs/langchain_v1 ( #38168 ) release(openai): 1.3.2 ( #38130 ) hotfix(openai): switch version ( #38123 ) release(openai): 1.4.0 ( #38120 ) docs: refresh README installation and resources ( #38119 ) test(core,langchain): update tests for explicit deserialization allowlists ( #38118 ) release(core): 1.4.7 ( #38111 ) release(anthropic): 1.4.6 ( #38105 ) release(langchain): 1.3.9 ( #38104 ) fix(langchain,anthropic): confine file-search results and tighten anthropic allowed_prefixes ( #38106 ) release(langchain): 1.3.8 ( #38096 ) style(core,langchain,langchain-classic,partners): replace double backticks in docstrings ( #38095 ) release(core): 1.4.6 ( #38061 ) chore(langchain): add overloads to create_agent ( #34309 ) chore(infra): bump mypy to 2.1 and unify type-check config across the monorepo ( #36470 ) fix(langchain): support async middleware decorator typing ( #34584 ) fix(langchain): tighten structured output model fallbacks ( #38042 ) release(anthropic): 1.4.5 ( #38036 ) hotfix(core): bump lockfile(s) ( #38032 ) refactor(langchain): refactor test_create_agent_tool_validation ( #34443 ) release(langchain): 1.3.7 ( #38024 ) style(langchain): add ruff rules ARG ( #34435 ) feat(langchain): add ProviderToolSearchMiddleware ( #37969 ) chore(langchain): activate mypy warn_return_any ( #34249 ) test(langchain): mark legacy trigger view for 2.0 removal ( #38002 ) release(langchain): 1.3.6 ( #38001 ) fix(langchain): preserve summarization trigger compatibility ( #38000 ) release(langchain): 1.3.5 ( #37998 ) feat(langchain): port AND-capable trigger conditions to SummarizationMiddleware ( #34576 ) hotfix(openai): min core dep ( #37990 ) feat(openai): support apply_patch built-in tool ( #37157 ) chore: bump pyarrow from 21.0.0 to 23.0.1 in /libs/langchain_v1 ( #37930 ) chore: bump dependencies ( #37892 ) chore: bump aiohttp from 3.13.4 to 3.14.0 in /libs/langchain_v1 ( #37888 ) release(langchain): 1.3.4 ( #37861 ) fix(langchain): improve HITL rejection guidance ( #37859 ) release(langchain): 1.3.3 ( #37843 ) chore(langchain): bump langgraph to 1.2.4 ( #37857 ) chore(langchain): loosen langgraph dep range ( #37855 ) feat(langchain): project subagent runs onto typed run.subagents channel ( #37739 ) feat(langchain): add interrupt_mode and when predicate to HumanInTheLoopMiddleware ( #37579 ) chore(langchain): bump to 1.3.2, require langgraph>=1.2.2 ( #37703 ) fix(langchain): land final answer in last AIMessage for TodoListMiddleware ( #37643 ) feat(langchain): redact streamed PII in flight on PIIMiddleware ( #37616 ) chore(infra): bump langchain-tests floor to 1.1.9 ( #37610 ) release(standard-tests): 1.1.9 ( #37609 ) feat(langchain): register stream transformers on middleware ( #37591 ) chore: bump idna from 3.11 to 3.15 in /libs/langchain_v1 ( #37534 ) ci(infra): harden Dependabot version-bound preservation ( #37510 ) refactor(langchain): clean redundancy ifelse. ( #37448 ) hotfix: bump lockfiles ( #37508 ) chore(core,langchain,openai): refresh stale OpenAI model references ( #37487 ) fix(langchain): sort glob_search results by mtime (newest first) ( #37462 ) chore: bump langsmith from 0.7.31 to 0.8.0 in /libs/langchain_v1 ( #37391 ) release(langchain): 1.3.1 ( #37454 ) fix(langchain): alias Bedrock providers in summarization token check ( #37453 ) release(langchain): 1.3.0 ( #37361 ) chore(infra): merge v1.4 into master ( #37350 ) chore: bump urllib3 from 2.6.3 to 2.7.0 in /libs/langchain_v1 ( #37328 ) release(langchain): 1.2.18 ( #37250 ) revert: feat(langchain): ls_agent_type tag on create_agent calls ( #37249 ) chore(langchain-classic): deprecate hub, limit loads/dumps ( #37234 ) refactor(langchain-classic): retarget deprecations to create_agent , other chores ( #37164 ) chore(langchain,langchain-classic): uncomment optional deps ( #37163 ) release(fireworks): 1.2.1 ( #37113 ) release(langchain): 1.2.17 ( #37110 ) feat(langchain): add respond decision to HITL middleware ( #37095 ) release(langchain): 1.2.16 ( #37085 ) chore(docs): update x handle references ( #37081 ) release(anthropic): 1.4.2 ( #37061 ) perf(langchain): stop inlining agent state into tool-dispatch Send s ( #36960 ) docs(langchain): correct import paths in agent middleware docstrings ( #36987 ) hotfix: bump min core versions ( #36996 ) release(openai): 1.2.1 ( #36995 ) feat(core): add content-block-centric streaming (v2) ( #36834 ) fix(fireworks): honor max_retries ( #36973 ) release(openai): 1.2.0 ( #36961 ) docs(langchain): correct import path in ModelCallLimitMiddleware docstring ( #36895 ) feat(langchain): ls_agent_type tag on create_agent calls ( #36774 ) release(core): release 1.3.0 ( #36851 ) chore: bump langsmith from 0.6.3 to 0.7.31 in /libs/langchain_v1 ( #36800 ) chore(deps): bump pytest to 9.0.3 ( #36801 ) chore: bump pytest from 9.0.2 to 9.0.3 in /libs/langchain_v1 ( #36717 ) chore: bump pillow from 12.1.1 to 12.2.0 in /libs/langchain_v1 ( #36710 ) test(langchain): test cache hit/miss on lru ( #36659 ) perf(langchain): add lru cache when resolving types ( #36649 ) perf(langchain): add another init test with middleware ( #36644 ) chore(core): reduce streaming metadata / perf ( #36588 ) perf(langchain): add benchmark command ( #36641 ) chore: bump cryptography from 46.0.6 to 46.0.7 in /libs/langchain_v1 ( #36619 ) docs(langchain): add missing baseten and litellm to init_chat_model ( #36562 ) release(core): 1.2.26 ( #36511 ) release: langchain v1.2.15 ( #36496 ) chore: bump aiohttp from 3.13.3 to 3.13.4 in /libs/langchain_v1 ( #36438 ) release(langchain): 1.2.14 ( #36396 ) chore: pygments>=2.20.0 across all packages ( CVE-2026-4539 ) ( #36385 ) test(langchain): cover runtime recursion limit override in create_agent ( #36376 ) perf(langchain): reduce init speed by 15% ( #36375 ) fix(langchain): update recursion limit for create_agent ( #36351 ) fix(infra): correct lint_diff relative paths in package makefiles ( #36333 ) chore: bump cryptography from 46.0.5 to 46.0.6 in /libs/langchain_v1 ( #36324 ) fix(langchain): recognize ChatAnthropicVertex in _get_approximate_token_counter ( #36320 ) chore(langchain): remove unnecessary description for toods list as a group ( #36315 ) chore(langchain): add async implementation to todolist and test ( #36313 ) chore(langchain): speed up todo list middleware init ( #36311 ) chore: bump requests from 2.32.5 to 2.33.0 in /libs/langchain_v1 ( #36241 ) chore(partners): bump langchain-core min to 1.2.21 ( #36183 ) fix(core,model-profiles): add missing ModelProfile fields, warn on schema drift ( #36129 ) fix(langchain,langchain-classic): update model provider classes for Azure AI Foundry ( #35812 ) release(langchain): 1.2.13 ( #36111 ) ci: suppress pytest streaming output in CI ( #36092 ) feat: Add LangSmith integration metadata to create_agent and init_chat_model ( #35810 ) ci: avoid unnecessary dep installs in lint targets ( #36046 ) chore: bump pyasn1 from 0.6.2 to 0.6.3 in /libs/langchain_v1 ( #36029 ) chore: bump pyjwt from 2.10.1 to 2.12.0 in /libs/langchain_v1 ( #36024 ) fix(langchain): export Runtime from agents.middleware ( #35975 ) chore: bump locks, lint ( #35985 ) fix(openai): add type: message to Responses API input items ( #35693 ) chore: bump black from 25.11.0 to 26.3.1 in /libs/langchain_v1 ( #35802 ) chore: bump orjson from 3.11.5 to 3.11.6 in /libs/langchain_v1 ( #35807 ) chore(langchain): add baseten to _BUILTIN_PROVIDERS ( #35777 ) release(langchain_v1): 1.2.12 ( #35770 ) feat: tracing for wrap model + tool call ( #35765 ) release(langchain_v1): 1.2.11 ( #35723 ) fix(langchain): normalize custom detector output to prevent KeyError in hash/mask strategies ( #35651 ) chore: bump the minor-and-patch group across 3 directories with 7 updates ( #35605 ) chore(langchain): switch refs from gemini-3 to gemini-3.1 ( #35535 ) chore: bump the langchain-deps group across 3 directories with 7 updates ( #35513 ) chore: bump langgraph-checkpoint from 3.0.1 to 4.0.0 in /libs/langchain_v1 ( #35445 ) chore: bump the langchain-deps group across 3 directories with 14 updates ( #35441 ) chore: bump google-cloud-aiplatform from 1.127.0 to 1.133.0 in /libs/langchain_v1 ( #35397 ) revert: add ChatAnthropicBedrockWrapper ( #35371 ) fix(langchain): support anthropic-bedrock in init_chat_model ( #35366 ) style: fix some ruff noqa ( #35321 ) fix(langchain): allow Gemini 3 models to use ProviderStrategy with tools ( #34464 ) docs: fix docstring inaccuracies and update outdated LangSmith URLs ( #35283 ) feat(openai): support automatic server-side compaction ( #35212 ) chore: bump the langchain-deps group across 3 directories with 8 updates ( #35257 ) feat(openrouter): add langchain-openrouter provider package ( #35211 ) style: bump ruff version to 0.15 ( #35042 ) chore(deps): bump pillow from 12.0.0 to 12.1.1 in /libs/langchain_v1 ( #35174 ) chore(core): raise more descriptive model error in init_chat_model ( #35167 ) chore(deps): bump langsmith from 0.4.42 to 0.6.3 in /libs/langchain_v1 ( #35149 ) chore(deps): bump cryptography from 46.0.3 to 46.0.5 in /libs/langchain_v1 ( #35148 ) release(langchain): 1.2.10 ( #35137 ) chore(deps): bump the langchain-deps group across 3 directories with 40 updates ( #35129 ) chore(deps): bump the langchain-deps group across 3 directories with 11 updates ( #35121 ) fix(langchain): fix token counting on partial message sequences ( #35101 ) refactor(langchain): rename _SUPPORTED_PROVIDERS -> _BUILTIN_PROVIDERS ( #35100 ) fix(langchain): normalize raw schemas in middleware response_format override ( #35019 ) feat: support state updates from wrap_model_call with command(s) ( #35033 ) test(langchain): types in test_tool_call_limit and test_model_retry ( #34629 ) fix(langchain): bump min core version and improve approximate token counting ( #35026 ) release: langchain 1.2.9 ( #35023 ) feat: threading context through create_agent flows + middleware ( #34978 ) chore: add make type target ( #35015 ) revert: "chore: add typing target in Makefile " ( #35013 ) chore: add typing target in Makefile ( #35012 ) revert: use usage metadata scaling in SummarizationMiddleware default token counter ( #35002 ) fix(langchain): use usage metadata scaling in SummarizationMiddleware default token counter ( #35001 ) fix(langchain): avoid UnboundLocalError when no AIMessage exists ( #34816 ) chore: enrich pyproject.toml files ( #34980 ) release(langchain): 1.2.8 ( #34976 ) chore(deps): bump the uv group across 20 directories with 3 updates ( #34941 ) fix: reuse ToolStrategy in agent factory to prevent name mismatch ( #34871 ) chore: upgrade urllib3 to 2.6.3 ( #34940 ) feat(langchain): add ToolCallRequest to middleware exports ( #34894 ) style(langchain): lint ( #34863 ) fix(langchain): blocking unit test ( #34866 ) test(langchain): use blockbuster to detect blocking calls in the async event loop ( #34777 ) release: langchain 1.2.7 ( #34854 ) feat: dynamic tool registration via middleware ( #34842 ) fix(langchain): strip trailing whitespace from the summarization prompt ( #34835 ) fix(langchain): improve grammar in SummarizationMiddleware system prompt ( #34834 ) docs(langchain): nit ( #34788 ) chore(deps): bump the uv group across 5 directories with 5 updates ( #34785 ) chore(deps): bump the uv group across 8 directories with 6 updates ( #34773 ) chore(core, langchain): add version consistency check pre-commit hooks ( #34782 ) release(langchain): 1.2.6 ( #34781 ) fix(langchain): SummarizationMiddleware signature mismatch & config invocation ( #34775 ) release(langchain): 1.2.5 ( #34772 ) fix(langchain): add metadata configuration to summarization model invocation ( #34763 ) feat(langchain): update summarization prompt ( #34754 ) chore: add tests for agent name metadata when streaming ( #34764 ) Revert "metadata" metadata release: langchain 1.2.4 ( #34755 ) chore(langchain): add agent name metadata ( #34743 ) chore: update twitter URLs ( #34736 ) chore: add tests for private state attr use (really, lack thereof) ( #34725 ) docs(langchain): clarify model ID usage for reliable behavior ( #34718 ) fix(langchain): tag messages generated from summarization ( #34693 ) fix(langchain): activate test_return_direct_spec tests, fix types ( #34565 ) chore(langchain): fix types in test_todo , test_tool_retry ( #34503 ) chore(langchain): fix types in test_shell_tool ( #34502 ) chore(langchain): activate mypy warn_return_any rule ( #34549 ) chore(langchain): fix types in test_tool_selection and test_tool_emulator ( #34499 ) chore(langchain): fix types in test_shell_execution_policies ( #34498 ) chore(langchain): improve ignore_missing_imports config ( #34551 ) test(langchain): complete and activate test_responses tests ( #34560 ) fix(langchain): activate mypy warn-unreachable ( #34553 ) chore(langchain): fix types in test_injected_runtime_create_agent , test_create_agent_tool_validation ( #34568 ) chore(langchain): fix types in test_response_format and test_state_schema ( #34571 ) chore(langchain): remove generic from FakeToolCallingModel ( #34572 ) chore(langchain): fix types in test_context_editing , test_agent_name , test_response_format_integration ( #34574 ) chore(langchain): fix types in test_overrides ( #34635 ) feat(langchain): add state to _ModelRequestOverrides ( #34692 ) chore(langchain): fix types in test_tools ( #34592 ) chore(langchain): fix types in test_summarization ( #34656 ) test(langchain): activate test_responses_spec tests ( #34564 ) style(langchain): fix some ruff preview rules ( #34663 ) chore(langchain): fix types in test_framework ( #34567 ) chore(langchain): fix types in memory_assert , conftest , conftest_checkpointer and conftest_store ( #34636 ) chore(langchain): fix types in test_system_message ( #34634 ) style: bump ruff version to 0.14.11 ( #34674 ) fix: remove relative imports ( #34680 ) fix(langchain,langchain-classic): more descriptive error msg when dep is not installed ( #34679 ) fix(langchain): infer provider from mixed-case prefixes ( #34672 ) fix: add test confirming we don't inject args based on args_schema alone ( #34677 ) release(langchain): 1.2.3 ( #34668 ) refactor(langchain): engage summarization based on reported usage_metadata ( #34632 ) fix(langchain): keep tool call / AIMessage pairings when summarizing ( #34609 ) test(langchain): cover chat model provider inference ( #34657 ) fix(langchain): fix copy-paste error on azure_openai embedding provider map ( #34655 ) fix(langchain): add test to verify version ( #34644 ) release(langchain): release 1.2.2 ( #34643 ) fix(langchain): handle parallel usage of the todo tool in planning middleware ( #34637 ) chore(langchain): fix types in test_wrap_model_call ( #34573 ) release(langchain): 1.2.1 ( #34622 ) fix(core,langchain): use get_buffer_string for message summarization ( #34607 ) chore(langchain): fix types in test_model_fallback ( #34615 ) chore(langchain): fix types in test_pii ( #34617 ) chore(langchain): add admonition around redaction_rules ( #34618 ) chore(langchain): fix types in test_composition ( #34580 ) chore(langchain): fix types in test_decorators ( #34583 ) chore(langchain): fix types in test_wrap_tool_call ( #34600 ) chore(langchain): fix types in test_model_call_limit_types ( #34601 ) chore(langchain): fix types in test_file_search and test_human_in_the_loop ( #34602 ) fix(core): exclude injected args from tool schema ( #34582 ) chore(langchain): fix types in test_diagram and test_sync_async_wrappers ( #34591 ) style(langchain): add ruff rule PLC0415 ( #34559 ) fix(langchain): resolve race condition in ShellSession.execute() ( #34535 ) fix(infra): use langchain_v1 for dev container deps ( #34534 ) chore(deps): bump mypy to v1.19 and ruff to v1.14 ( #34521 ) fix(langchain-classic): pass default to config.getoption ( #34034 ) style(langchain): add ruff rule RUF012 ( #34497 ) refactor(langchain): refactor optional imports logic ( #32813 ) style: add ruff ISC001 rule ( #34493 ) style(langchain): add TC ruff rules ( #34496 ) style(langchain): fix some ruff preview rules ( #34504 ) style(langchain): fix some PLC0415 rules ( #34475 ) style(langchain): add ruff rules PT ( #34434 ) feat(langchain): enhance init_chat_model with improved validation ( #34226 ) docs(langchain): Docstring improved to show Streaming custom events ( #34353 ) feat(langchain): Add support to google_genai provider in init_embeddings ( #34388 ) release(core): 1.2.3 ( #34421 ) release(openai): 1.1.6: update max input tokens for gpt-5 series ( #34419 ) release(openai): 1.1.5 ( #34409 ) feat(infra): add CI check for out of date lockfiles ( #34397 ) release(langchain): 1.2 ( #34373 ) fix(langchain): shell output multithreading race condition ( #34333 ) refactor(standard-tests): improve VCR config ( #33968 ) fix(huggingface): Helper logic for init_chat_model with HuggingFace backend ( #34259 ) chore(langchain): cleanup ruff config ( #32810 ) fix: little lint thing ( #34310 ) chore(langchain): check agents integration tests with mypy ( #34308 ) fix(langchain): add sentinel value to ProviderStrategy / strict ( #34290 ) chore(langchain): add end to end test for strict mode in provider strategy ( #34289 ) feat(langchain,openai): add strict flag to ProviderStrategy structured output ( #34149 ) feat(core,anthropic): extras on BaseTool ( #34120 ) release(langchain): 1.1.3 ( #34255 ) feat: add agent name to AIMessage ( #34254 ) chore(core): improve typing of messages utils functions ( #34225 ) feat(anthropic): add effort support ( #34116 ) feat(langchain): add support for Upstage (Solar) in init_chat_model ( #34220 ) release: langchain 1.1.2 ( #34210 ) fix: simplify summarization cutoff logic ( #34195 ) release: langchain 1.1.1 ( #34206 ) feat: Use uuid7 for run ids ( #34172 ) fix(langchain): (SummarizationMiddleware) adjust token counts based on model ( #34161 ) docs(langchain): docstrings for summariziation middleware types ( #34158 ) fix(langchain): add types to human_in_the_loop middleware ( #34137 ) docs(anthropic,core,langchain): updates ( #34106 ) release(langchain): 1.1 ( #34090 ) feat(langchain): support SystemMessage in create_agent 's system_prompt ( #34055 ) fix: don't reorder tool calls in HITL middleware ( #34023 ) chore(docs): fix a few refs syntax errors ( #34044 ) feat(model-profiles): distribute data across packages ( #34024 ) chore: add more robust test for runtime injection w/ explicit args_schema ( #34051 ) feat: ModelRetryMiddleware ( #34027 ) fix: deprecate setattr on ModelCallRequest ( #34022 ) style(langchain): fix some middleware ref syntax ( #33988 ) fix: resumable shell, works w/ interrupts ( #33978 ) feat(langchain): reference model profiles for provider strategy ( #33974 ) chore: increase coverage for shell, filesystem, and summarization middleware ( #33928 ) fix(anthropic): execute bash + file tools via tool node ( #33960 ) fix: adding missing async hooks ( #33957 ) docs: Fix doc links ( #33964 ) fix: add filesystem middleware in init ( #33955 ) chore(langchain): update deps ( #33951 ) fix(langchain, openai): backward compat for response_format ( #33945 ) fix(langchain, openai): fix create_agent / response_format for Responses API ( #33939 ) feat: refactor tests coverage ( #33927 ) chore: update README.md files ( #33919 ) feat(langchain): support async summarization in SummarizationMiddleware ( #33918 ) feat(langchain): (SummarizationMiddleware) support use of model context windows when triggering summarization ( #33825 ) chore(langchain): pass on reference docstrings (middleware) ( #33904 ) release(langchain): 1.0.5 ( #33893 ) revert: Support for SystemMessage in create_agent ( #33889 ) fix: bump up default recursion limit ( #33881 ) chore(langchain): Support for SystemMessage in create_agent ( #33640 ) fix(langchain): Update langchain-core dependency version ( #33775 ) style: some cleanup ( #33857 ) chore: attribute package change versions ( #33854 ) fix: don't trace conditional edges and no todos in input state ( #33842 ) release: langchain v1.0.4 ( #33839 ) fix: only increment thread count on successful executions ( #33837 ) fix: more robust tool call limit middleware ( #33817 ) feat(langchain): add model-profiles as optional dependency ( #33794 ) chore: use model IDs, latest anthropic models ( #33747 ) fix(langchain): use system_prompt in integration tests ( #33748 ) chore: remove mentions of sonnet 3.5 ( #33737 ) fix(langchain_v1): remove thread_model_call_count and run_model_call_count from tool node test ( #33725 ) release: core 1.0.2 and langchain 1.0.3 ( #33736 ) fix(langchain_v1): removed unsed functions in tool_call_limit middleware ( #33735 ) style: more refs fixes ( #33730 ) chore: move ToolNode improvements back to langgraph ( #33634 ) feat: support structured output retry middleware ( #33663 ) fix(langchain_v1): correct ref url ( #33715 ) style: more refs work ( #33707 ) feat(langchain): export UsageMetadata ( #33692 ) release(core): 1.0.1 ( #33639 ) chore(langchain_v1): bump version from 1.0.1 to 1.0.2 ( #33629 ) fix(langchain_v1): remove non llm controllable params from tool message on invocation failure ( #33625 ) release(langchain_v1): 1.0.1 ( #33610 ) fix(langchain_v1): ToolRuntime default for args ( #33606 ) style: more refs polishing ( #33601 ) docs(langchain): update reference documentation to note moved embeddings modules ( #33600 ) style(anthropic): use aliases for model names ( #33590 ) chore: update pyproject.toml url entries ( #33587 ) release(langchain_v1): v1.0.0 ( #33588 ) fix: shell tool middleware ( #33589 ) feat(langchain_v1): Python 3.14 support ( #33560 ) fix(langchain,langchain_v1): enable huggingface optional dep ( #33586 ) fix(langchain): conditional tools -> end edge when all client side calls return direct ( #33550 ) chore(langchain_v1): relax typing on input state ( #33552 ) feat(langchain_v1): Add ShellToolMiddleware and ClaudeBashToolMiddleware ( #33527 ) feat(langchain): file-search middleware ( #33551 ) release: joint rcs for core + langchain ( #33549 ) chore(langchain): allow injection of ToolRuntime and generic ToolRuntime[ContextT, StateT] ( #33546 ) fix(langchain): revert conditional edge from tools to end ( #33520 ) ( #33539 ) release(langchain): cut rc ( #33534 ) release(core): 1.0.0rc2 ( #33530 ) docs(langchain_v1): remove absent arg descriptions ( #33529 ) fix(langchain): conditional edge from tools to end ( #33520 ) fix(langchain_v1): relax tool node validation to allow claude text editing tools ( #33512 ) chore(langchain): update state schema doc ( #33524 ) chore(langchain_v1): adding back state_schema to create_agent ( #33519 ) chore(langchain): use runtime not tool_runtime for injected tool arg ( #33522 ) feat(langchain_v1): tool retry middleware ( #33503 ) chore(langchain_v1): switch order of params in ToolRuntime ( #33518 ) feat(langchain_v1): injected runtime ( #33500 ) style: more sweeping refs work ( #33513 ) style: more work for refs ( #33508 ) release(langchain_v1): 1.0.0a15 ( #33505 ) fix(langchain_v1): keep state to relevant middlewares for tool/model call limits ( #33493 ) release(core): 1.0.0rc1 ( #33497 ) docs: update package READMEs ( #33488 ) chore(langchain_v1): remove invocation request ( #33482 ) feat(langchain_v1): add async implementations to wrap_model_call ( #33467 ) fix(langchain_v1): can not import "wrap_tool_call" from agents.… ( #33472 ) feat(langchain_v1): add override to model request and tool call request ( #33465 ) docs: create_agent style and clarify system_prompt ( #33470 ) fix(langchain): rename PlanningMiddleware to TodoListMiddleware ( #33476 ) fix(langchain_v1): export ModelResponse from agents.middleware ( #33453 ) ( #33454 ) chore(langchain_v1,anthropic): migrate anthropic middleware to langchain_anthropic ( #33463 ) chore(langchain_v1): use args for HITL ( #33442 ) chore(langchain_v1): bump release version ( #33440 ) chore(langchain_v1): improve error message ( #33433 ) chore(langchain_v1): remove langchain_text_splitters from test group ( #33425 ) chore(langchain_v1): stricter handling of sync vs. async for wrap_model_call and wrap_tool_call ( #33429 ) chore(langchain_v1): further namespace clean up ( #33428 ) feat(langchain_v1): add async implementation for wrap_tool_call ( #33420 ) chore(langchain_v1): tool error exceptions ( #33424 ) feat(langchain_v1): expand message exports ( #33419 ) style: fix tables, capitalization ( #33417 ) chore(langchain_v1): add RemoveMessage ( #33416 ) release(langchain_v1): v1.0.0a13 ( #33415 ) fix(langchain_v1): out of date docstring ( #33414 ) chore(langchain_v1): update on_tool_call to wrap_tool ( #33410 ) chore(langchain_v1): update wrap_on_model return ( #33408 ) feat(langchain_v1): tool emulator ( #33357 ) feat(langchain_v1): refactoring HITL API ( #33397 ) style: .. code-block:: admonition translations ( #33400 ) style: address Sphinx double-backtick snippet syntax ( #33389 ) chore: update Sphinx links to markdown ( #33386 ) style: remove more Optional syntax ( #33371 ) chore(langchain_v1): rename on_model_call to wrap_model_call ( #33370 ) chore(langchain_v1): update the uv lock file ( #33369 ) chore(langchain_v1): replace modify model request with on model call ( #33368 ) chore(langchain): add unit tests for wrap_tool_call decorator ( #33367 ) chore(langchain_v1): rename on_tool_call to wrap_tool_call ( #33366 ) chore(langchain_v1): add runtime and context to model request ( #33365 ) chore(langchain_v1): update on_tool_call to regular callbacks ( #33364 ) style: monorepo pass for refs ( #33359 ) chore(langchain_v1): simplify on model call logic ( #33358 ) chore: fix dropdown default open admonition in refs ( #33354 ) chore(langchain_v1): remove unused internal namespace ( #33352 ) feat(langchain_v1): add on_tool_call middleware hook ( #33329 ) feat(langchain_v1): on_model_call middleware ( #33328 ) remove runtime where not needed fix(langchain_v1): injection logic in tool node ( #33344 ) chore: enrich pyproject.toml files with links to new references, others ( #33343 ) chore: clean up pyproject.toml files, use core a7 ( #33334 ) chore(langchain): clean Makefile ( #33335 ) fix(langchain_v1): fix edges when there's no middleware ( #33321 ) release(langchain_v1): 1.0.0a12 ( #33314 ) chore(langchain_v1): rename model_request node -> model ( #33310 ) release(langchain_v1): 1.0.0a11 ( #33307 ) chore(langchain_v1): remove support for ToolNode in create_agent ( #33306 ) feat(langchain_v1): simplify to use ONE agent ( #33302 ) chore(langchain_v1): remove text splitters from langchain v1 namespace ( #33297 ) chore(langchain_v1): expose rate_limiters from langchain_core ( #33305 ) fix(langchain_v1): tool selector should use last human message ( #33294 ) feat(langchain_v1): before_agent and after_agent hooks ( #33279 ) feat(langchain_v1): Implement Context Editing Middleware ( #33267 ) feat(openai): enable stream_usage when using default base URL and client ( #33205 ) chore(infra): pdm -> hatchling ( #33289 ) feat(langchain_v1): Add retry_model_request middleware hook, add ModelFallbackMiddleware ( #33275 ) fix(langchain_v1): linting fixes for llm tool selector ( #33278 ) feat(langchain_v1): add llm selection middleware ( #33272 ) feat(langchain_v1): represent server side tools in modifyModelRequest and update tool handling ( #33274 ) feat(langchain_v1): Implement PIIMiddleware ( #33271 ) fix(langchain_v1): dynamic response format ( #33273 ) chore(langchain_v1): remove union return type in init_embeddings ( #33062 ) feat(langchain_v1): Add ToolCallLimitMiddleware ( #33269 ) chore(langchain_v1): change modifyModelRequest back to tools (#33270) fix(langchain_v1): handle switching resposne format strategy based on model identity (#33259) feat(langchain_v1): implement nicer devx for dynamic prompt (#33264) feat(langchain_v1): description generator for HITL middleware (#33195) chore(core,langchain,langchain_v1)!: remove globals from langchain-v1, update globals in langchain-classic, langchain-core (#33251) chore(langchain_v1)!: Remove ToolNode from agents (#33250) feat(langchain): model call limits (#33178) chore: delete deprecated items (#33192) chore(langchain_v1): uncomment some optional deps (#33244) docs: v1 docs updates (#33173) release: v1.0.0 (#32567) feat(langchain_v1): update messages namespace (#33207) feat(langchain): use decorators for jumps instead (#33179) feat(langchain_v1): add async support for create_agent (#33175) chore(langchain_v1): use list[str] for modifyModelRequest (#33166) feat(langchain): Using Structured Response as Key in Output Schema for Middleware Agent (#33159) chore(langchain_v1): expose middleware decorators and selected messages (#33163) feat(langchain): todo middleware (#33152) fix(langchain): handle gpt-5 model name in init_chat_model (#33148) fix(langchain): add context_management to Anthropic chat model init (#33150) fix(langchain): fix response action for HITL (#33131) chore(langchain_v1): move tool node to tools namespace (#33132) docs: more standardization (#33124) docs: standardize .. code-block directive usage (#33122) docs: correct ported over directives (#33121) chore: bump ruff version to 0.13 (#33043) chore: bump locks (#33114) release(langchain): v1.0.0a9 (#33098) fix(langchain): extra arg for anthropic caching, __end__ -> end for jump_to (#33097) fix(langchain_v1): version equality check (#33095) release(langchain): 1.0.0a8 (#33090) feat(langchain): improvements to anthropic prompt caching (#33058) style: repo linting pass (#33089) fix(langchain): need to inject all state for tools registered by middleware (#33087) chore(langchain): renaming for HITL (#33067) chore(langchain): simplifying HITL condition (#33065) fix(langchain_v1): only interrupt if at least one ToolConfig value is True (#33064) feat(langchain): new decorator pattern for dynamically generated middleware (#33053) fix(langchain): HITL bug causing dupe interrupt (#33052) chore: update pyproject.toml files, remove codespell (#33028) release(langchain): 1.0.0a6 (#33024) fix(langchain): use state schema as input schema to middleware nodes (#33023) feat(langchain): dynamic system prompt middleware (#33006) feat(langchain): improved HITL patterns (#32996) chore: restore commented out optional deps (#32971) chore: bump mypy version to 1.18 (#32914) release(langchain): v1.0.0a5 (#32917) fix(langchain): use messages from model request (#32908) fix(core): resolve mermaid node id collisions when special chars are used (#32857) revert: "chore: remove ruff target-version" (#32895) chore: remove ruff target-version (#32880) chore(docs): update package README s (#32869) feat(langchain): support PEP604 ( | union) in tool node error handlers (#32861) chore(langchain): add ruff rule E501 in langchain_v1 (#32812) chore(langchain): add ruff rule UP007 in langchain_v1 (#32811) chore(langchain): enable ruff docstring-code-format in langchain_v1 (#32855) chore(core): enable ruff docstring-code-format (#32834) feat(langchain): middleware support in create_agent (#32828) fix(langchain): fix mypy versions in langchain_v1 (#32816) chore(langchain): cleanup langchain_v1 mypy config (#32809) chore(langchain): add ruff rules D for langchain_v1 (#32808) fix(langchain): update init version (#32793) release(langchain): v1.0.0a3 (#32791) chore(langchain): rename create_react_agent -> create_agent (#32789) chore(langchain): remove upper bound at v1 for core (#32737) chore(langchain): also bump text splitters (#32722) chore(langchain): use latest core (#32720) chore(langchain): revert back to static versioning for now (#32719) release(langchain): v1.0.0a1 (#32718) feat(langchain): revamped create_react_agent (#32705) chore(langchain): remove untested chains for first alpha (#32710) chore(langchain): drop Python 3.9 to prep for v1 (#32704) chore: adress pytest-asyncio deprecation warnings + other nits (#32696) chore: update references to use the latest version of Claude-3.5 Sonnet (#32594) docs: update outdated README.md content (#32540) fix(tests): add anthropic_proxy to configurable test parameters (for v1) chore: formatting across codebase (#32466) feat(openai): minimal and verbosity (#32455) feat(langchain): add stuff and map reduce chains (#32333) fix: use new Google model names in examples (#32288) fix: update bar_model to use the correct model version claude-3-7-sonnet-20250219 (#32284) refactor: remove references to unsupported model claude-3-sonnet-20240229 (#32281) fix: formatting issues in docstrings (#32265) feat(docs): improve devx, fix Makefile targets (#32237) chore(langchain_v1): clean anything uncertain (#32228) feat(langchain): v1 scaffolding (#32166)